Full Taxonomy

Alliant Audiences

MDM ID:

Segment:

Category:

Sub-Category:

Vertical 1:

Vertical 2:

HH/Ind:

Audience Size (PII):

MDM ID	Segment	Category	Sub-Category	Vertical 1	Vertical 2	HH/Ind	Modeled/Known/Inferred	Audience Size (PII)	Estimated Audience Size (Digital)	Segment Description
161.812	Diesel	Auto	Fuel Type	Auto		Household	Known	1,54	3,23	Households that own a vehicle with a diesel engine, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
161.813	Electric	Auto	Fuel Type	Auto		Household	Known	87,24	183,20	Households that own an electric vehicle, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
161.814	Flex-Fuel	Auto	Fuel Type	Auto		Household	Known	5,10	10,70	Households that own a vehicle with a flex-fuel engine, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
161.821	Hybrid	Auto	Fuel Type	Auto		Household	Known	1,26	2,65	Households that own a hybrid vehicle, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
11.989	Clunker Owner In-Market for New Car	Auto	In-Market	Auto		Household	Modeled	3,68	7,72	Built from automotive ownership data that is sourced from nationwide dealership and service department records. The source data is used as a study group, that is then joined to an offline cooperative of multichannel transactions (via digital and offline channels from DTC businesses) , demographics and life stage data (recent home move, new parents, retired, etc.) to identify households who have the same indicators of those who have previously made vehicle purchases.
11.984	In-Market for Financing	Auto	In-Market	Auto	Financial Services	Household	Modeled	16,94	35,57	Built from automotive ownership data that is sourced from nationwide dealership and service department records. The source data is used as a study group, that is then joined to an offline cooperative of multichannel transactions (via digital and offline channels from DTC businesses) , demographics and life stage data (recent home move, new parents, retired, etc.) to identify households who have the same indicators of those who have previously made vehicle purchases.
11.985	In-Market for Insurance	Auto	In-Market	Auto	Financial Services	Household	Modeled	25,50	53,55	Built from automotive ownership data that is sourced from nationwide dealership and service department records. The source data is used as a study group, that is then joined to an offline cooperative of multichannel transactions (via digital and offline channels from DTC businesses) , demographics and life stage data (recent home move, new parents, retired, etc.) to identify households who have the same indicators of those who have previously made vehicle purchases.
11.991	In-Market for New Economy Car	Auto	In-Market	Auto		Household	Modeled	16,60	34,87	Built from automotive ownership data that is sourced from nationwide dealership and service department records. The source data is used as a study group, that is then joined to an offline cooperative of multichannel transactions (via digital and offline channels from DTC businesses) , demographics and life stage data (recent home move, new parents, retired, etc.) to identify households who have the same indicators of those who have previously made vehicle purchases.
11.990	In-Market for New Green Car	Auto	In-Market	Auto		Household	Modeled	15,94	33,47	Built from automotive ownership data that is sourced from nationwide dealership and service department records. The source data is used as a study group, that is then joined to an offline cooperative of multichannel transactions (via digital and offline channels from DTC businesses) , demographics and life stage data (recent home move, new parents, retired, etc.) to identify households who have the same indicators of those who have previously made vehicle purchases.
161.810	In-Market for New Large SUV	Auto	In-Market	Auto		Household	Modeled	9,28	19,48	Built from automotive ownership data that is sourced from nationwide dealership and service department records. The source data is used as a study group, that is then joined to an offline cooperative of multichannel transactions (via digital and offline channels from DTC businesses) , demographics and life stage data (recent home move, new parents, retired, etc.) to identify households who have the same indicators of those who have previously purchased large SUVs.
11.992	In-Market for New Luxury Car	Auto	In-Market	Auto		Household	Modeled	16,98	35,66	Built from automotive ownership data that is sourced from nationwide dealership and service department records. The source data is used as a study group, that is then joined to an offline cooperative of multichannel transactions (via digital and offline channels from DTC businesses) , demographics and life stage data (recent home move, new parents, retired, etc.) to identify households who have the same indicators of those who have previously made vehicle purchases.
11.993	In-Market for New Mini Van	Auto	In-Market	Auto		Household	Modeled	14,07	29,55	Built from automotive ownership data that is sourced from nationwide dealership and service department records. The source data is used as a study group, that is then joined to an offline cooperative of multichannel transactions (via digital and offline channels from DTC businesses) , demographics and life stage data (recent home move, new parents, retired, etc.) to identify households who have the same indicators of those who have previously made vehicle purchases.
11.994	In-Market for New Sedan	Auto	In-Market	Auto		Household	Modeled	13,20	27,72	Built from automotive ownership data that is sourced from nationwide dealership and service department records. The source data is used as a study group, that is then joined to an offline cooperative of multichannel transactions (via digital and offline channels from DTC businesses) , demographics and life stage data (recent home move, new parents, retired, etc.) to identify households who have the same indicators of those who have previously made vehicle purchases.
161.811	In-Market for New Small SUV	Auto	In-Market	Auto		Household	Modeled	13,45	28,25	Built from automotive ownership data that is sourced from nationwide dealership and service department records. The source data is used as a study group, that is then joined to an offline cooperative of multichannel transactions (via digital and offline channels from DTC businesses) , demographics and life stage data (recent home move, new parents, retired, etc.) to identify households who have the same indicators of those who have previously purchased small SUVs.
11.995	In-Market for New Sports car	Auto	In-Market	Auto		Household	Modeled	524,24	1,10	Built from automotive ownership data that is sourced from nationwide dealership and service department records. The source data is used as a study group, that is then joined to an offline cooperative of multichannel transactions (via digital and offline channels from DTC businesses) , demographics and life stage data (recent home move, new parents, retired, etc.) to identify households who have the same indicators of those who have previously made vehicle purchases.
11.996	In-Market for New SUV	Auto	In-Market	Auto		Household	Modeled	13,64	28,65	Built from automotive ownership data that is sourced from nationwide dealership and service department records. The source data is used as a study group, that is then joined to an offline cooperative of multichannel transactions (via digital and offline channels from DTC businesses) , demographics and life stage data (recent home move, new parents, retired, etc.) to identify households who have the same indicators of those who have previously made vehicle purchases.
11.997	In-Market for New Truck	Auto	In-Market	Auto		Household	Modeled	17,96	37,71	Built from automotive ownership data that is sourced from nationwide dealership and service department records. The source data is used as a study group, that is then joined to an offline cooperative of multichannel transactions (via digital and offline channels from DTC businesses) , demographics and life stage data (recent home move, new parents, retired, etc.) to identify households who have the same indicators of those who have previously made vehicle purchases.
11.986	In-Market for New Vehicle	Auto	In-Market	Auto		Household	Modeled	19,55	41,06	Built from automotive ownership data that is sourced from nationwide dealership and service department records. The source data is used as a study group, that is then joined to an offline cooperative of multichannel transactions (via digital and offline channels from DTC businesses) , demographics and life stage data (recent home move, new parents, retired, etc.) to identify households who have the same indicators of those who have previously made vehicle purchases.
11.998	In-Market for New Wagon	Auto	In-Market	Auto		Household	Modeled	17,91	37,62	Built from automotive ownership data that is sourced from nationwide dealership and service department records. The source data is used as a study group, that is then joined to an offline cooperative of multichannel transactions (via digital and offline channels from DTC businesses) , demographics and life stage data (recent home move, new parents, retired, etc.) to identify households who have the same indicators of those who have previously made vehicle purchases.
11.987	In-Market for Parts & Service	Auto	In-Market	Auto		Household	Modeled	35,91	75,41	Built from automotive ownership data that is sourced from nationwide dealership and service department records. The source data is used as a study group, that is then joined to an offline cooperative of multichannel transactions (via digital and offline channels from DTC businesses) , demographics and life stage data (recent home move, new parents, retired, etc.) to identify households who have the same indicators of those who have previously made vehicle purchases.
11.988	In-Market for Used Vehicle	Auto	In-Market	Auto		Household	Modeled	79,56	167,08	Built from automotive ownership data that is sourced from nationwide dealership and service department records. The source data is used as a study group, that is then joined to an offline cooperative of multichannel transactions (via digital and offline channels from DTC businesses) , demographics and life stage data (recent home move, new parents, retired, etc.) to identify households who have the same indicators of those who have previously made vehicle purchases.
11.999	Multi-Car Owner In-Market for New Car	Auto	In-Market	Auto		Household	Modeled	21,58	45,31	Built from automotive ownership data that is sourced from nationwide dealership and service department records. The source data is used as a study group, that is then joined to an offline cooperative of multichannel transactions (via digital and offline channels from DTC businesses) , demographics and life stage data (recent home move, new parents, retired, etc.) to identify households who have the same indicators of those who have previously made vehicle purchases.
12.163	Acura Switchers	Auto	Loyalty	Auto		Household	Inferred	1,85	3,89	Households that Alliant has identified to be a defector from Acura, meaning they have owned an Acura but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.164	Audi Switchers	Auto	Loyalty	Auto		Household	Inferred	1,07	2,24	Households that Alliant has identified to be a defector from Audi, meaning they have owned a Audi but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.165	Auto Class Switchers	Auto	Loyalty	Auto		Household	Inferred	19,18	40,29	Households that Alliant has identified to be a defector from auto classes, meaning they do not have a repeat history of purchasing a specific vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.166	Auto Make Switchers	Auto	Loyalty	Auto		Household	Inferred	61,69	129,55	Households that Alliant has identified to be a defector from auto makes, meaning they do not have a repeat history of purchasing a specific vehicle make. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.129	Auto Style Loyalists	Auto	Loyalty	Auto		Household	Inferred	29,70	62,37	Households that Alliant has identified to be loyal in their continued purchase of an auto style. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.167	Auto Style Switchers	Auto	Loyalty	Auto		Household	Inferred	17,48	36,72	Households that Alliant has identified to be a defector from auto style, meaning they do not have a repeat history of purchasing that vehicle style. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.130	BMW Loyalists	Auto	Loyalty	Auto		Household	Inferred	309,29	649,50	Households that Alliant has identified to be loyal in their continued purchase of a BMW. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.168	BMW Switchers	Auto	Loyalty	Auto		Household	Inferred	2,32	4,87	Households that Alliant has identified to be a defector from BMW, meaning they have owned a BMW but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.132	Cadillac Loyalists	Auto	Loyalty	Auto		Household	Inferred	220,65	463,37	Households that Alliant has identified to be loyal in their continued purchase of a Cadillac. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.170	Cadillac Switchers	Auto	Loyalty	Auto		Household	Inferred	2,24	4,70	Households that Alliant has identified to be a defector from Cadillac, meaning they have owned a Cadillac but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.133	Chevrolet Loyalists	Auto	Loyalty	Auto		Household	Inferred	4,07	8,55	Households that Alliant has identified to be loyal in their continued purchase of a Chevrolet. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.171	Chevrolet Switchers	Auto	Loyalty	Auto		Household	Inferred	15,10	31,71	Households that Alliant has identified to be a defector from Chevrolet, meaning they have owned a Chevrolet but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.173	Convertible Switchers	Auto	Loyalty	Auto		Household	Inferred	1,54	3,24	Households that Alliant has identified to be a defector from convertibles, meaning they have owned a convertible but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.135	Coupe 2-door Loyalists	Auto	Loyalty	Auto		Household	Inferred	766,49	1,61	Households that Alliant has identified to be loyal in their continued purchase of a coupe 2-door. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.174	Coupe 2-door Switchers	Auto	Loyalty	Auto		Household	Inferred	4,38	9,20	Households that Alliant has identified to be a defector from coupe 2-doors, meaning they have owned a coupe 2-door but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.136	Crossover Loyalists	Auto	Loyalty	Auto		Household	Inferred	993,28	2,09	Households that Alliant has identified to be loyal in their continued purchase of a crossover. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.137	Dodge Loyalists	Auto	Loyalty	Auto		Household	Inferred	1,06	2,23	Households that Alliant has identified to be loyal in their continued purchase of a Dodge. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.176	Dodge Switchers	Auto	Loyalty	Auto		Household	Inferred	8,82	18,52	Households that Alliant has identified to be a defector from Dodge, meaning they have owned a Dodge but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.138	Ford Loyalists	Auto	Loyalty	Auto		Household	Inferred	4,49	9,43	Households that Alliant has identified to be loyal in their continued purchase of a Ford. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.177	Ford Switchers	Auto	Loyalty	Auto		Household	Inferred	16,10	33,80	Households that Alliant has identified to be a defector from Ford, meaning they have owned a Ford but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.139	Full Size Car Loyalists	Auto	Loyalty	Auto		Household	Inferred	2,43	5,11	Households that Alliant has identified to be loyal in their continued purchase of a full size car. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.178	Full Size Car Switchers	Auto	Loyalty	Auto		Household	Inferred	6,99	14,68	Households that Alliant has identified to be a defector from full size Cars, meaning they have owned a full size car but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.140	Full Size SUV Loyalists	Auto	Loyalty	Auto		Household	Inferred	4,61	9,68	Households that Alliant has identified to be loyal in their continued purchase of a full size SUV. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.179	Full Size SUV Switchers	Auto	Loyalty	Auto		Household	Inferred	9,49	19,93	Households that Alliant has identified to be a defector from full size SUV, meaning they have owned a full size SUV but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.141	Full Size Truck Loyalists	Auto	Loyalty	Auto		Household	Inferred	6,67	14,01	Households that Alliant has identified to be loyal in their continued purchase of a full size truck. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.180	Full Size Truck Switchers	Auto	Loyalty	Auto		Household	Inferred	10,25	21,53	Households that Alliant has identified to be a defector from full size truck, meaning they have owned a full size truck but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.181	Full Size Van Switchers	Auto	Loyalty	Auto		Household	Inferred	587,54	1,23	Households that Alliant has identified to be a defector from full size van, meaning they have owned a full size van but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.142	GMC Loyalists	Auto	Loyalty	Auto		Household	Inferred	386,21	811,03	Households that Alliant has identified to be loyal in their continued purchase of a GMC. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.182	GMC Switchers	Auto	Loyalty	Auto		Household	Inferred	4,36	9,15	Households that Alliant has identified to be a defector from GMC, meaning they have owned a GMC but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.143	Hatchback Loyalists	Auto	Loyalty	Auto		Household	Inferred	657,22	1,38	Households that Alliant has identified to be loyal in their continued purchase of a hatchback. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.144	Honda Loyalists	Auto	Loyalty	Auto		Household	Inferred	1,62	3,41	Households that Alliant has identified to be loyal in their continued purchase of a Honda. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.184	Honda Switchers	Auto	Loyalty	Auto		Household	Inferred	9,80	20,59	Households that Alliant has identified to be a defector from Honda, meaning they have owned a Honda but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.145	Hyundai Loyalists	Auto	Loyalty	Auto		Household	Inferred	496,27	1,04	Households that Alliant has identified to be loyal in their continued purchase of a Hyundai. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.185	Hyundai Switchers	Auto	Loyalty	Auto		Household	Inferred	4,53	9,52	Households that Alliant has identified to be a defector from Hyundai, meaning they have owned a Hyundai but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.186	Infiniti Switchers	Auto	Loyalty	Auto		Household	Inferred	1,10	2,32	Households that Alliant has identified to be a defector from Infiniti, meaning they have owned a Infiniti but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.146	Jeep Loyalists	Auto	Loyalty	Auto		Household	Inferred	455,97	957,54	Households that Alliant has identified to be loyal in their continued purchase of a Jeep. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.188	Jeep Switchers	Auto	Loyalty	Auto		Household	Inferred	5,27	11,06	Households that Alliant has identified to be a defector from Jeep, meaning they have owned a Jeep but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.147	Kia Loyalists	Auto	Loyalty	Auto		Household	Inferred	295,04	619,58	Households that Alliant has identified to be loyal in their continued purchase of a Kia. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.189	Kia Switchers	Auto	Loyalty	Auto		Household	Inferred	3,37	7,08	Households that Alliant has identified to be a defector from Kia, meaning they have owned a Kia but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.190	Land Rover Switchers	Auto	Loyalty	Auto		Household	Inferred	327,12	686,94	Households that Alliant has identified to be a defector from Land Rover, meaning they have owned a Land Rover but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.148	Lexus Loyalists	Auto	Loyalty	Auto		Household	Inferred	345,76	726,10	Households that Alliant has identified to be loyal in their continued purchase of a Lexus. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.191	Lexus Switchers	Auto	Loyalty	Auto		Household	Inferred	1,38	2,90	Households that Alliant has identified to be a defector from Lexus, meaning they have owned a Lexus but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.192	Lincoln Switchers	Auto	Loyalty	Auto		Household	Inferred	871,58	1,83	Households that Alliant has identified to be a defector from Lincoln, meaning they have owned a Lincoln but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.193	Luxury Car Switchers	Auto	Loyalty	Auto		Household	Inferred	152,04	319,29	Households that Alliant has identified to be a defector from luxury cars, meaning they have owned a luxury car but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.194	Mazda Switchers	Auto	Loyalty	Auto		Household	Inferred	1,65	3,46	Households that Alliant has identified to be a defector from Mazda, meaning they have owned a Mazda but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.149	Mercedes-Benz Loyalists	Auto	Loyalty	Auto		Household	Inferred	294,34	618,11	Households that Alliant has identified to be loyal in their continued purchase of a Mercedes-Benz. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.195	Mercedes-Benz Switchers	Auto	Loyalty	Auto		Household	Inferred	1,18	2,48	Households that Alliant has identified to be a defector from Mercedes-Benz, meaning they have owned a Mercedes-Benz but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.150	Mid Size Car Loyalists	Auto	Loyalty	Auto		Household	Inferred	6,01	12,61	Households that Alliant has identified to be loyal in their continued purchase of a mid-size car. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.196	Mid Size SUV Switchers	Auto	Loyalty	Auto		Household	Inferred	461,54	969,24	Households that Alliant has identified to be a defector from midsize SUVs, meaning they have owned a mid-size SUV but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.197	Mid-Size Car Switchers	Auto	Loyalty	Auto		Household	Inferred	6,68	14,03	Households that Alliant has identified to be a defector from mid-size cars, meaning they have owned a mid-size car but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.198	Mid-Size Truck Switchers	Auto	Loyalty	Auto		Household	Inferred	1,13	2,37	Households that Alliant has identified to be a defector from mid-size trucks, meaning they have owned a mid-sized truck but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.151	Mini Van Loyalists	Auto	Loyalty	Auto		Household	Inferred	1,78	3,75	Households that Alliant has identified to be loyal in their continued purchase of a mini van. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.200	Mini Van Switchers	Auto	Loyalty	Auto		Household	Inferred	3,35	7,04	Households that Alliant has identified to be a defector from mini vans, meaning they have owned a mini van but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.152	Nissan Loyalists	Auto	Loyalty	Auto		Household	Inferred	883,64	1,86	Households that Alliant has identified to be loyal in their continued purchase of a Nissan. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.202	Nissan Switchers	Auto	Loyalty	Auto		Household	Inferred	4,23	8,88	Households that Alliant has identified to be a defector from Nissan, meaning they have owned a Nissan but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.153	Pickup Truck Loyalist	Auto	Loyalty	Auto		Household	Inferred	8,37	17,59	Households that Alliant has identified to be loyal in their continued purchase of a pickup truck. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.203	Pickup Truck Switchers	Auto	Loyalty	Auto		Household	Inferred	7,38	15,50	Households that Alliant has identified to be a defector from pickup trucks, meaning they have owned a pickup truck but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.154	Sedan Loyalists	Auto	Loyalty	Auto		Household	Inferred	14,42	30,28	Households that Alliant has identified to be loyal in their continued purchase of a sedan. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.205	Sedan Switchers	Auto	Loyalty	Auto		Household	Inferred	9,46	19,87	Households that Alliant has identified to be a defector from sedans, meaning they have owned a sedans but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.155	Small Car Loyalists	Auto	Loyalty	Auto		Household	Inferred	10,31	21,64	Households that Alliant has identified to be loyal in their continued purchase of a small car. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.206	Small Car Switchers	Auto	Loyalty	Auto		Household	Inferred	8,07	16,95	Households that Alliant has identified to be a defector from small cars, meaning they have owned a small car but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.156	Small SUV Loyalists	Auto	Loyalty	Auto		Household	Inferred	3,49	7,33	Households that Alliant has identified to be loyal in their continued purchase of a small SUV. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.207	Small SUV Switchers	Auto	Loyalty	Auto		Household	Inferred	5,56	11,68	Households that Alliant has identified to be a defector from small SUV, meaning they have owned a Small SUV but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.157	Small Truck Loyalists	Auto	Loyalty	Auto		Household	Inferred	358,03	751,85	Households that Alliant has identified to be loyal in their continued purchase of a small truck. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.208	Small Truck Switchers	Auto	Loyalty	Auto		Household	Inferred	1,76	3,70	Households that Alliant has identified to be a defector from Small Truck, meaning they have owned a small truck but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.209	Subaru Switchers	Auto	Loyalty	Auto		Household	Inferred	1,44	3,03	Households that Alliant has identified to be a defector from Subaru, meaning they have owned a Subaru but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.158	Toyota Loyalists	Auto	Loyalty	Auto		Household	Inferred	2,51	5,26	Households that Alliant has identified to be loyal in their continued purchase of a Toyota. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.211	Toyota Switchers	Auto	Loyalty	Auto		Household	Inferred	7,04	14,77	Households that Alliant has identified to be a defector from Toyota, meaning they have owned a Toyota but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.212	Utility Van Switchers	Auto	Loyalty	Auto		Household	Inferred	8,86	18,60	Households that Alliant has identified to be a defector from utility vans, meaning they have owned a utility van but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.160	Van Loyalists	Auto	Loyalty	Auto		Household	Inferred	1,96	4,12	Households that Alliant has identified to be loyal in their continued purchase of a van. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.214	Volkswagen Switchers	Auto	Loyalty	Auto		Household	Inferred	1,69	3,56	Households that Alliant has identified to be a defector from Volkswagen, meaning they have owned a Volkswagen but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.215	Volvo Switchers	Auto	Loyalty	Auto		Household	Inferred	656,31	1,38	Households that Alliant has identified to be a defector from Volvo, meaning they have owned a Volvo but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.161	Wagon Loyalists	Auto	Loyalty	Auto		Household	Inferred	966,39	2,03	Households that Alliant has identified to be loyal in their continued purchase of a wagon. Identified by known historic auto ownership data through nationwide dealership and service department records.
12.216	Wagon Switchers	Auto	Loyalty	Auto		Household	Inferred	2,92	6,13	Households that Alliant has identified to be a defector from wagons, meaning they have owned a wagon but do not have a repeat history of purchasing that vehicle type. Identified by known historic auto ownership data through nationwide dealership and service department records.
161.822	0 – 30k Miles	Auto	Mileage Ranges	Auto		Household	Known	11,87	24,93	Households that own a vehicle with mileage ranging between 0-30k, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
161.828	100K+ Miles	Auto	Mileage Ranges	Auto		Household	Known	5,62	11,81	Households that own a vehicle with mileage over 100k, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
161.823	30k – 50k Miles	Auto	Mileage Ranges	Auto		Household	Known	4,56	9,58	Households that own a vehicle with mileage ranging between 30-50k, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
161.825	50k – 75k Miles	Auto	Mileage Ranges	Auto		Household	Known	3,47	7,28	Households that own a vehicle with mileage ranging between 50-75k, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
161.827	75k – 100k Miles	Auto	Mileage Ranges	Auto		Household	Known	4,05	8,51	Households that own a vehicle with mileage ranging between 75-100k, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.109	Auto Lease Propensity	Auto	Ownership	Auto		Household	Modeled	12,93	27,16	This audience consists of households in the top 20% of a model predicting the likelihood that a member leases a car. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
12.098	Emerging Consumers - Clunker Owners	Auto	Ownership	Auto		Household	Modeled	6,04	12,68	Households that own a clunker car, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the bottom 50% of buying activity in the Alliant cooperative.)
12.099	Emerging Consumers - Economy Car Owners	Auto	Ownership	Auto		Household	Modeled	13,14	27,59	Households that own an economy car, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the bottom 50% of buying activity in the Alliant cooperative.)
12.100	Emerging Consumers - Green Car Owners	Auto	Ownership	Auto		Household	Modeled	3,16	6,63	Households that own a green car, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the bottom 50% of buying activity in the Alliant cooperative.)
12.101	Emerging Consumers - Luxury Car Owners	Auto	Ownership	Auto		Household	Modeled	2,61	5,49	Households that own a luxury car, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the bottom 50% of buying activity in the Alliant cooperative.)
12.102	Emerging Consumers - Mini Van Owners	Auto	Ownership	Auto		Household	Modeled	2,60	5,46	Households that own a mini van, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the bottom 50% of buying activity in the Alliant cooperative.)
12.103	Emerging Consumers - Multi-Car Owners	Auto	Ownership	Auto		Household	Modeled	13,51	28,38	Households that own multiple cars, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the bottom 50% of buying activity in the Alliant cooperative.)
12.104	Emerging Consumers - Sedan Owners	Auto	Ownership	Auto		Household	Modeled	14,55	30,55	Households that own a sedan, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the bottom 50% of buying activity in the Alliant cooperative.)
12.105	Emerging Consumers - Sports Car Owners	Auto	Ownership	Auto		Household	Modeled	330,04	693,08	Households that own a sports car, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the bottom 50% of buying activity in the Alliant cooperative.)
12.106	Emerging Consumers - SUV Owners	Auto	Ownership	Auto		Household	Modeled	9,42	19,79	Households that own a SUV, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the bottom 50% of buying activity in the Alliant cooperative.)
12.107	Emerging Consumers - Truck Owners	Auto	Ownership	Auto		Household	Modeled	6,72	14,11	Households that own a truck, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the bottom 50% of buying activity in the Alliant cooperative.)
12.108	Emerging Consumers - Wagon Owners	Auto	Ownership	Auto		Household	Modeled	2,26	4,74	Households that own a wagon, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the bottom 50% of buying activity in the Alliant cooperative.)
12.113	Empowered Consumers - Clunker Owners	Auto	Ownership	Auto		Household	Modeled	8,17	17,16	Households that own a clunker car, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the top 50% of buying activity in the Alliant cooperative.)
12.114	Empowered Consumers - Economy Car Owners	Auto	Ownership	Auto		Household	Modeled	21,05	44,20	Households that own an economy car, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the top 50% of buying activity in the Alliant cooperative.
12.115	Empowered Consumers - Green Car Owners	Auto	Ownership	Auto		Household	Modeled	5,92	12,43	Households that own a green car, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the top 50% of buying activity in the Alliant cooperative.)
12.116	Empowered Consumers - Luxury Car Owners	Auto	Ownership	Auto		Household	Modeled	4,94	10,38	Households that own luxury cars, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the top 50% of buying activity in the Alliant cooperative.)
12.117	Empowered Consumers - Mini Van Owners	Auto	Ownership	Auto		Household	Modeled	4,49	9,44	Households that own mini vans, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the top 50% of buying activity in the Alliant cooperative.)
12.118	Empowered Consumers - Multi-Car Owners	Auto	Ownership	Auto		Household	Modeled	24,62	51,70	Households that own multiple cars, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the top 50% of buying activity in the Alliant cooperative.)
12.119	Empowered Consumers - Sedan Owners	Auto	Ownership	Auto		Household	Modeled	22,53	47,31	Households that own a sedan, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the top 50% of buying activity in the Alliant cooperative.)
12.120	Empowered Consumers - Sports Car Owners	Auto	Ownership	Auto		Household	Modeled	664,58	1,40	Households that own a sports car, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the top 50% of buying activity in the Alliant cooperative.)
12.121	Empowered Consumers - SUV Owners	Auto	Ownership	Auto		Household	Modeled	17,14	36,00	Households that own a SUV, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the top 50% of buying activity in the Alliant cooperative.)
12.122	Empowered Consumers - Truck Owners	Auto	Ownership	Auto		Household	Modeled	11,54	24,23	Households that own a truck, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the top 50% of buying activity in the Alliant cooperative.)
12.123	Empowered Consumers - Wagon Owners	Auto	Ownership	Auto		Household	Modeled	4,22	8,86	Households that own a wagon, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the top 50% of buying activity in the Alliant cooperative.)
12.110	Hybrid Cars Propensity	Auto	Ownership	Auto		Household	Modeled	15,05	31,62	This audience consists of households in the top 20% of a model predicting the likelihood that they own or lease at least one hybrid vehicle. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
12.111	Motorcycle Owner Propensity	Auto	Ownership	Auto		Household	Modeled	15,81	33,20	This audience consists of households in the top 20% of a model predicting the likelihood that they own a new or used motorcycle. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
12.003	Own a BMW	Auto	Ownership	Auto		Household	Known	3,38	7,09	Households that own a BMW, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.005	Own a Cadillac	Auto	Ownership	Auto		Household	Known	3,32	6,96	Households that own a Cadillac, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.006	Own a Chevrolet	Auto	Ownership	Auto		Household	Known	23,85	50,09	Households that own a Chevrolet, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.007	Own a Chevrolet Blazer	Auto	Ownership	Auto		Household	Known	1,19	2,50	Households that own a Chevrolet Blazer, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.009	Own a Chevrolet Camaro	Auto	Ownership	Auto		Household	Known	933,04	1,96	Households that own a Chevrolet Camaro, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.012	Own a Chevrolet Cruze	Auto	Ownership	Auto		Household	Known	1,03	2,16	Households that own a Chevrolet Cruze, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.013	Own a Chevrolet Equinox	Auto	Ownership	Auto		Household	Known	1,76	3,69	Households that own a Chevrolet Equinox, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.014	Own a Chevrolet Impala	Auto	Ownership	Auto		Household	Known	2,39	5,02	Households that own a Chevrolet Impala, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.016	Own a Chevrolet Malibu	Auto	Ownership	Auto		Household	Known	2,52	5,30	Households that own a Chevrolet Malibu, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.020	Own a Chevrolet Suburban	Auto	Ownership	Auto		Household	Known	1,66	3,49	Households that own a Chevrolet Suburban, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.021	Own a Chevrolet Tahoe	Auto	Ownership	Auto		Household	Known	2,06	4,32	Households that own a Chevrolet Tahoe, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.023	Own a Chrysler	Auto	Ownership	Auto		Household	Known	6,20	13,03	Households that own a Chrysler, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.024	Own a Dodge	Auto	Ownership	Auto		Household	Known	13,84	29,07	Households that own a Dodge, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.025	Own a Dodge Caravan	Auto	Ownership	Auto		Household	Known	2,93	6,15	Households that own a Dodge Caravan, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.030	Own a Dodge RAM	Auto	Ownership	Auto		Household	Known	3,08	6,48	Households that own a Dodge RAM, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.032	Own a Ford	Auto	Ownership	Auto		Household	Known	25,33	53,19	Households that own a Ford, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.034	Own a Ford Escape	Auto	Ownership	Auto		Household	Known	2,59	5,44	Households that own a Ford Escape, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.036	Own a Ford Expedition	Auto	Ownership	Auto		Household	Known	1,73	3,63	Households that own a Ford Expedition, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.037	Own a Ford Explorer	Auto	Ownership	Auto		Household	Known	3,99	8,37	Households that own a Ford Explorer, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.039	Own a Ford Fusion	Auto	Ownership	Auto		Household	Known	1,82	3,81	Households that own a Ford Fusion, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.043	Own a Ford Truck	Auto	Ownership	Auto		Household	Known	7,14	15,00	Households that own a Ford Truck, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.045	Own a GMC	Auto	Ownership	Auto		Household	Known	6,77	14,22	Households that own a GMC, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.046	Own a GMC Envoy	Auto	Ownership	Auto		Household	Known	771,66	1,62	Households that own a GMC Envoy, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.047	Own a GMC Sierra	Auto	Ownership	Auto		Household	Known	2,54	5,33	Households that own a GMC Sierra, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.049	Own a Honda	Auto	Ownership	Auto		Household	Known	14,07	29,55	Households that own a Honda, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.050	Own a Honda Accord	Auto	Ownership	Auto		Household	Known	5,39	11,31	Households that own a Honda Accord, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.051	Own a Honda Civic	Auto	Ownership	Auto		Household	Known	3,87	8,13	Households that own a Honda Civic, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.052	Own a Honda CRV	Auto	Ownership	Auto		Household	Known	2,57	5,39	Households that own a Honda CRV, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.053	Own a Honda Odyssey	Auto	Ownership	Auto		Household	Known	1,94	4,07	Households that own a Honda Odyssey, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.054	Own a Honda Pilot	Auto	Ownership	Auto		Household	Known	1,47	3,08	Households that own a Honda Pilot, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.055	Own a Hyundai	Auto	Ownership	Auto		Household	Known	6,22	13,07	Households that own a Hyundai, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.058	Own a Jaguar	Auto	Ownership	Auto		Household	Known	401,89	843,96	Households that own a Jaguar, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.059	Own a Jeep	Auto	Ownership	Auto		Household	Known	7,68	16,13	Households that own a Jeep, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.060	Own a Jeep Cherokee	Auto	Ownership	Auto		Household	Known	1,21	2,54	Households that own a Jeep Cherokee, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.062	Own a Jeep Wrangler	Auto	Ownership	Auto		Household	Known	2,17	4,55	Households that own a Jeep Wrangler, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.063	Own a Kia	Auto	Ownership	Auto		Household	Known	4,61	9,69	Households that own a Kia, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.064	Own a Land Rover	Auto	Ownership	Auto		Household	Known	463,65	973,66	Households that own a Land Rover, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.065	Own a Lexus	Auto	Ownership	Auto		Household	Known	3,36	7,05	Households that own a Lexus, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.066	Own a Lincoln	Auto	Ownership	Auto		Household	Known	2,13	4,48	Households that own a Lincoln, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.067	Own a Mazda	Auto	Ownership	Auto		Household	Known	3,97	8,35	Households that own a Mazda, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.068	Own a Mercedes-Benz	Auto	Ownership	Auto		Household	Known	3,07	6,44	Households that own a Mercedes-Benz, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.070	Own a Mini	Auto	Ownership	Auto		Household	Known	490,59	1,03	Households that own a Mini, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.071	Own a Mitsubishi	Auto	Ownership	Auto		Household	Known	2,12	4,45	Households that own a Mitsubishi, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.072	Own a Nissan	Auto	Ownership	Auto		Household	Known	10,78	22,64	Households that own a Nissan, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.073	Own a Nissan Altima	Auto	Ownership	Auto		Household	Known	3,01	6,33	Households that own a Nissan Altima, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.074	Own a Nissan Frontier	Auto	Ownership	Auto		Household	Known	815,68	1,71	Households that own a Nissan Frontier, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.075	Own a Nissan Maxima	Auto	Ownership	Auto		Household	Known	1,30	2,74	Households that own a Nissan Maxima, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.076	Own a Nissan Pathfinder	Auto	Ownership	Auto		Household	Known	874,85	1,84	Households that own a Nissan Pathfinder, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.077	Own a Nissan Sentra	Auto	Ownership	Auto		Household	Known	1,57	3,30	Households that own a Nissan Sentra, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.081	Own a Porsche	Auto	Ownership	Auto		Household	Known	382,38	803,00	Households that own a Porsche, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.083	Own a Subaru	Auto	Ownership	Auto		Household	Known	3,04	6,38	Households that own a Subaru, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.084	Own a Toyota	Auto	Ownership	Auto		Household	Known	17,75	37,28	Households that own a Toyota, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.085	Own a Toyota 4Runner	Auto	Ownership	Auto		Household	Known	1,29	2,70	Households that own a Toyota 4Runner, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.086	Own a Toyota Avalon	Auto	Ownership	Auto		Household	Known	878,88	1,85	Households that own a Toyota Avalon, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.087	Own a Toyota Camry	Auto	Ownership	Auto		Household	Known	5,16	10,84	Households that own a Toyota Camry, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.088	Own a Toyota Corolla	Auto	Ownership	Auto		Household	Known	3,28	6,88	Households that own a Toyota Corolla, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.089	Own a Toyota Highlander	Auto	Ownership	Auto		Household	Known	1,46	3,07	Households that own a Toyota Highlander, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.090	Own a Toyota Prius	Auto	Ownership	Auto		Household	Known	1,27	2,67	Households that own a Toyota Prius, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.091	Own a Toyota RAV4	Auto	Ownership	Auto		Household	Known	1,72	3,61	Households that own a Toyota RAV4, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.092	Own a Toyota Sienna	Auto	Ownership	Auto		Household	Known	1,39	2,93	Households that own a Toyota Sienna, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.093	Own a Toyota Tacoma	Auto	Ownership	Auto		Household	Known	1,73	3,62	Households that own a Toyota Tacoma, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.094	Own a Toyota Tundra	Auto	Ownership	Auto		Household	Known	1,31	2,75	Households that own a Toyota Tundra, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.095	Own a Volkswagen	Auto	Ownership	Auto		Household	Known	4,01	8,43	Households that own a Volkswagen, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.096	Own a Volvo	Auto	Ownership	Auto		Household	Known	1,46	3,07	Households that own a Volvo, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.001	Own an Acura	Auto	Ownership	Auto		Household	Known	2,54	5,34	Households that own an Acura, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.002	Own an Audi	Auto	Ownership	Auto		Household	Known	1,47	3,10	Households that own an Audi, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.056	Own an Infiniti	Auto	Ownership	Auto		Household	Known	1,54	3,23	Households that own an Infiniti, identified by nationwide dealership and service department records. These households are also known multichannel buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
240.368	C-Level Executives Under 50	B2B	Age	Demographics		Household	Known	1,09	2,29	The C-level Executives Under 50 audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.377	Executives In Market for New Vehicle	B2B	Auto	Auto		Household	Modeled	1,60	3,36	The Executives In Market for New Vehicle audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.405	Executives with Apple Buyer Propensity	B2B	Brands	Tech		Household	Modeled	2,89	6,08	The Executives with Apple Buyer Interest audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.407	Executives with Dell Buyer Propensity	B2B	Brands	Tech		Household	Modeled	2,51	5,27	The Executives with Dell Buyer Interest audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.409	Executives with Lyft Buyer Propensity	B2B	Brands	Travel		Household	Modeled	2,13	4,47	The Executives with Lyft Buyer Interest audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.406	Executives with Microsoft Buyer Propensity	B2B	Brands	Tech		Household	Modeled	2,43	5,11	The Executives with Microsoft Buyer Interest audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.408	Executives with Samsung Buyer Propensity	B2B	Brands	Tech		Household	Modeled	2,74	5,76	The Executives with Samsung Buyer Interest audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.412	Executives with AT&T Buyer Propensity	B2B	Brands	Telecom		Household	Modeled	2,90	6,10	The Executives with AT&T Buyer Interest audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.411	Executives with T-Mobile Buyer Propensity	B2B	Brands	Telecom		Household	Modeled	2,43	5,10	The Executives with T-Mobile Buyer Interest audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.410	Executives with Uber Buyer Propensity	B2B	Brands	Travel		Household	Modeled	2,18	4,58	The Executives with Uber Buyer Interest audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.413	Executives with Verizon Buyer Propensity	B2B	Brands	Telecom		Household	Modeled	2,49	5,23	The Executives with Verizon Buyer Interest audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.373	Small Business Owners at Home who use AMEX	B2B	Card Type	Home		Household	Known	199,35	418,63	The Small Business Owners who use AMEX audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.372	Small Business Owners at Home who use Discover Card	B2B	Card Type	Home		Household	Known	141,12	296,35	The Small Business Owners who use Discover Card audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.371	Small Business Owners at Home who use Mastercard	B2B	Card Type	Home		Household	Known	324,47	681,39	The Small Business Owners who use Mastercard audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.374	Small Business Owners at Home who use Visa	B2B	Card Type	Home		Household	Known	466,69	980,05	The Small Business Owners who use Visa audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.369	Executives with Children 0-12	B2B	Family	Demographics		Household	Known	1,64	3,43	The Executives with Children 0-12 audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.370	Executives with Teens	B2B	Family	Demographics		Household	Known	1,07	2,24	The Executives with Teens audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.399	Female C-Suite at Home	B2B	Gender	Home		Household	Known	1,00	2,11	The Female C-Suite audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.397	Female Executives at Home	B2B	Gender	Home		Household	Known	3,83	8,04	The Female Executives audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.400	Male C-Suite at Home	B2B	Gender	Home		Household	Known	917,18	1,93	The Male C-Suite audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.398	Male Executives at Home	B2B	Gender	Home		Household	Known	2,47	5,19	The Male Executives audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.379	Executives Who Have Recently Moved	B2B	New Movers	Demographics		Household	Known	216,21	454,04	The Executives Who Have Recently Moved audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.381	Architecture & Engineering Professionals at Home	B2B	Occupation	Home		Household	Known	118,98	249,86	The Architecture & Engineering Professionals audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.382	Arts & Entertainment Professionals at Home	B2B	Occupation	Home		Household	Known	280,25	588,53	The Arts & Entertainment Professionals audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.383	Construction & Maintenance Professionals at Home	B2B	Occupation	Home		Household	Known	406,37	853,38	The Construction & Maintenance Professionals audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.392	Education Professionals at Home	B2B	Occupation	Home		Household	Modeled	537,34	1,13	The Education Professionals audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.380	Finance & Banking Professionals at Home	B2B	Occupation	Home		Household	Known	435,41	914,37	The Finance & Banking Professionals audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.384	Food Prep & Hospitality Professionals at Home	B2B	Occupation	Home		Household	Known	132,89	279,07	The Food Prep & Hospitality Professionals audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.391	Healthcare Professionals at Home	B2B	Occupation	Home		Household	Known	462,51	971,26	The Healthcare Professionals audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.385	IT Professionals at Home	B2B	Occupation	Home		Household	Known	191,17	401,45	The IT Professionals audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.386	Legal Professionals at Home	B2B	Occupation	Home		Household	Known	112,80	236,87	The Legal Professionals audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.390	Real Estate & Insurance Professionals at Home	B2B	Occupation	Home		Household	Known	697,60	1,46	The Real Estate & Insurance Professionals audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.388	Religious Professionals at Home	B2B	Occupation	Home		Household	Known	122,54	257,33	The Religious Professionals audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.387	Sales & Marketing Professionals at Home	B2B	Occupation	Home		Household	Known	351,31	737,75	The Sales & Marketing Professionals audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.389	Sports & Training Professionals at Home	B2B	Occupation	Home		Household	Known	245,73	516,02	The Sports & Training Professionals audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.376	Democrat Executives	B2B	Party Affiliations	Politics		Household	Known	948,13	1,99	The Democrat Executives audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.375	Republican Executives	B2B	Party Affiliations	Politics		Household	Known	972,84	2,04	The Republican Executives audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.395	Executives Interested in New York Post	B2B	Publications	Media & Entertainment		Household	Modeled	3,12	6,55	The Executives Interested in New York Post audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.394	Executives Interested in New York Times	B2B	Publications	Media & Entertainment		Household	Modeled	2,42	5,09	The Executives Interested in New York Times audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.393	Executives Interested in Wall Street Journal	B2B	Publications	Media & Entertainment		Household	Modeled	1,87	3,93	The Executives Interested in Wall Street Journal audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.396	Executives Interested in Washington Post	B2B	Publications	Media & Entertainment		Household	Modeled	2,86	6,00	The Executives Interested in Washington Post audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.403	C-Level Executives with JetBlue Interest	B2B	Travel	Travel		Household	Modeled	620,84	1,30	The C-Level Executives with JetBlue Interest audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.404	C-Level Executives with United Airlines Interest	B2B	Travel	Travel		Household	Modeled	705,86	1,48	The C-Level Executives with United Airlines Interest audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.401	Domestic Traveling Executives	B2B	Travel	Travel		Household	Known	2,30	4,82	The Domestic Traveling Executives audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
240.402	International Traveling Executives	B2B	Travel	Travel		Household	Known	2,25	4,73	The International Traveling Executives audience enables you to reach this niche segment outside of the office, across devices. They are also known direct-to-consumer buyers within the Alliant DataHub.
294.350	Top Golf	Brand Propensities	Activities & Interests	Sports		Household	Modeled	13,82	29,03	This audience consists of households in the top 15-20% of a model predicting a purchase from Top Golf. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.357	Alcoholic Beverages	Brand Propensities	Alcoholic Beverages	Food & Beverage		Household	Modeled	14,90	31,29	This audience consists of households in the top 15-20% of a model predicting a purchase from the Alcoholic Beverages category. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.124	Saucey Buyer Propensity	Brand Propensities	Alcoholic Beverages	Food & Beverage		Household	Modeled	14,02	29,44	This audience consists of households in the top 15-20% of a model predicting a purchase from Saucey. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.239	Total wine & more Buyer Propensity	Brand Propensities	Alcoholic Beverages	Food & Beverage		Household	Modeled	15,33	32,20	This audience consists of households in the top 15-20% of a model predicting a purchase from Total wine & more. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.264	WSJwine Buyer Propensity	Brand Propensities	Alcoholic Beverages	Food & Beverage		Household	Modeled	14,76	30,99	This audience consists of households in the top 15-20% of a model predicting a purchase from WSJwine. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.712	Bevmo Buyer Propensity	Brand Propensities	Alcoholic Beverages	Food & Beverage		Household	Modeled	15,60	32,75	This audience consists of households in the top 10-20% of a model predicting a purchase from Bevmo. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.220	Abercrombie & Fitch Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	16,40	34,43	This audience consists of households in the top 15-20% of a model predicting a purchase from Abercrombie & Fitch. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.221	Adidas Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,98	31,45	This audience consists of households in the top 15-20% of a model predicting a purchase from Adidas. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.474	Adore Me Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,37	28,07	This audience consists of households in the top 15-20% of a model predicting a purchase from Adore Me. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.222	ALDO Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	15,57	32,69	This audience consists of households in the top 15-20% of a model predicting a purchase from ALDO. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.076	Allbirds Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,29	30,02	This audience consists of households in the top 15-20% of a model predicting a purchase from Allbirds. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.223	American Eagle Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,27	27,86	This audience consists of households in the top 15-20% of a model predicting a purchase from American Eagle. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.225	Ann Taylor Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,37	30,18	This audience consists of households in the top 15-20% of a model predicting a purchase from Ann Taylor. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.226	Anthropologie Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	15,48	32,51	This audience consists of households in the top 15-20% of a model predicting a purchase from Anthropologie. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.261	Ashley Stewart Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	12,63	26,52	This audience consists of households in the top 15-20% of a model predicting a purchase from Ashley Stewart. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.228	Asics Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,96	29,32	This audience consists of households in the top 15-20% of a model predicting a purchase from Asics. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.229	asos Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	16,65	34,97	This audience consists of households in the top 15-20% of a model predicting a purchase from asos. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.230	Banana Republic Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	15,41	32,36	This audience consists of households in the top 15-20% of a model predicting a purchase from Banana Republic. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.231	Bare Necessities Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	10,10	21,22	This audience consists of households in the top 15-20% of a model predicting a purchase from Bare Necessities. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.278	BCBG Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	18,40	38,63	This audience consists of households in the top 15-20% of a model predicting a purchase from BCBG. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.232	Belk Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	11,15	23,41	This audience consists of households in the top 15-20% of a model predicting a purchase from Belk. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.235	Bloomingdale's Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	15,19	31,90	This audience consists of households in the top 15-20% of a model predicting a purchase from Bloomingdale's. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.236	Blue Nile Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,25	29,94	This audience consists of households in the top 15-20% of a model predicting a purchase from Blue Nile. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.285	Bonobos Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	15,32	32,17	This audience consists of households in the top 15-20% of a model predicting a purchase from Bonobos. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.237	boohoo Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,56	30,58	This audience consists of households in the top 15-20% of a model predicting a purchase from boohoo. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.238	Boot Barn Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	12,37	25,97	This audience consists of households in the top 15-20% of a model predicting a purchase from Boot Barn. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.286	Brandy Melville Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,31	30,05	This audience consists of households in the top 15-20% of a model predicting a purchase from Brandy Melville. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.239	Brooks Brothers Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,88	29,15	This audience consists of households in the top 15-20% of a model predicting a purchase from Brooks Brothers. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.298	Burlington Coat Factory Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,58	28,53	This audience consists of households in the top 15-20% of a model predicting a purchase from Burlington Coat Factory. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.301	Calvin Klein Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	18,67	39,21	This audience consists of households in the top 15-20% of a model predicting a purchase from Calvin Klein. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.241	Carters Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	11,75	24,68	This audience consists of households in the top 15-20% of a model predicting a purchase from Carters. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.510	Casual Male XL Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,74	30,96	This audience consists of households in the top 15-20% of a model predicting a purchase from Casual Male XL. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.242	Chico's Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	6,64	13,94	This audience consists of households in the top 15-20% of a model predicting a purchase from Chico's. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.316	Chico's FAS Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,20	27,71	This audience consists of households in the top 15-20% of a model predicting a purchase from Chico’s FAS. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.317	Club Monaco Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	15,06	31,62	This audience consists of households in the top 15-20% of a model predicting a purchase from Club Monaco. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.318	Cole Haan Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	16,02	33,64	This audience consists of households in the top 15-20% of a model predicting a purchase from Cole Haan. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.246	Converse Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	12,70	26,66	This audience consists of households in the top 15-20% of a model predicting a purchase from Converse. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.300	Cotton On	Brand Propensities	Apparel	Retail		Household	Modeled	14,66	30,78	This audience consists of households in the top 15-20% of a model predicting a purchase from Cotton On. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.247	Crocs Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,60	28,56	This audience consists of households in the top 15-20% of a model predicting a purchase from Crocs. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.250	Dillards Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	12,53	26,31	This audience consists of households in the top 15-20% of a model predicting a purchase from Dillards. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.137	Dolce Vita Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,14	29,69	This audience consists of households in the top 15-20% of a model predicting a purchase from Dolce Vita. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.251	DSW Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,28	27,89	This audience consists of households in the top 15-20% of a model predicting a purchase from DSW. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.252	Duluth Trading Company Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	11,18	23,49	This audience consists of households in the top 15-20% of a model predicting a purchase from Duluth Trading Company. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.253	Eddie Bauer Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	12,31	25,85	This audience consists of households in the top 15-20% of a model predicting a purchase from Eddie Bauer. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.254	Express Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	16,44	34,52	This audience consists of households in the top 15-20% of a model predicting a purchase from Express. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.255	Fabletics Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	15,02	31,54	This audience consists of households in the top 15-20% of a model predicting a purchase from Fabletics. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.108	Famous Footwear Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	12,39	26,03	This audience consists of households in the top 15-20% of a model predicting a purchase from Famous Footwear. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.256	Foot Locker Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,80	28,98	This audience consists of households in the top 15-20% of a model predicting a purchase from Foot Locker. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.258	Forever 21 Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,46	30,36	This audience consists of households in the top 15-20% of a model predicting a purchase from Forever 21. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.259	Fossil Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,93	29,26	This audience consists of households in the top 15-20% of a model predicting a purchase from Fossil. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.260	Gap Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,47	30,38	This audience consists of households in the top 15-20% of a model predicting a purchase from Gap. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.093	Guess Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,98	29,35	This audience consists of households in the top 15-20% of a model predicting a purchase from Guess. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.264	H&M Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	15,47	32,49	This audience consists of households in the top 15-20% of a model predicting a purchase from H&M. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.265	Hanes Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	12,35	25,94	This audience consists of households in the top 15-20% of a model predicting a purchase from Hanes. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.098	Hot Topic Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,06	27,44	This audience consists of households in the top 15-20% of a model predicting a purchase from Hot Topic. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.269	Hush Puppies Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	17,95	37,69	This audience consists of households in the top 15-20% of a model predicting a purchase from Hush Puppies. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.208	Indochino Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	15,24	32,01	This audience consists of households in the top 15-20% of a model predicting a purchase from Indochino. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.269	J.Crew Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,80	28,98	This audience consists of households in the top 15-20% of a model predicting a purchase from J.Crew. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.270	J.JILL Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,15	27,61	This audience consists of households in the top 15-20% of a model predicting a purchase from J.JILL. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.211	JanSport Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	11,89	24,98	This audience consists of households in the top 15-20% of a model predicting a purchase from JanSport. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.271	JCPenney Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	11,54	24,23	This audience consists of households in the top 15-20% of a model predicting a purchase from JCPenney. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.272	Jordan Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	11,44	24,01	This audience consists of households in the top 15-20% of a model predicting a purchase from Jordan. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.213	JoS. A. Bank Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	16,56	34,77	This audience consists of households in the top 15-20% of a model predicting a purchase from JoS. A. Bank. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.273	Journeys Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	12,18	25,57	This audience consists of households in the top 15-20% of a model predicting a purchase from Journeys. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.214	JustFab Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	12,76	26,79	This audience consists of households in the top 15-20% of a model predicting a purchase from JustFab. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.273	Kate Spade Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,07	29,55	This audience consists of households in the top 15-20% of a model predicting a purchase from Kate Spade. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.275	Keds Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	12,61	26,47	This audience consists of households in the top 15-20% of a model predicting a purchase from Keds. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.177	Kipling Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	11,71	24,60	This audience consists of households in the top 15-20% of a model predicting a purchase from Kipling. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.274	L.L.Bean Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	12,00	25,20	This audience consists of households in the top 15-20% of a model predicting a purchase from L.L.Bean. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.275	Lady Foot Locker Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	11,24	23,61	This audience consists of households in the top 15-20% of a model predicting a purchase from Lady Foot Locker. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.277	Lane Bryant Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,38	28,10	This audience consists of households in the top 15-20% of a model predicting a purchase from Lane Bryant. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.278	Levi's Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	18,27	38,37	This audience consists of households in the top 15-20% of a model predicting a purchase from Levi's. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.279	Lids Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	12,59	26,44	This audience consists of households in the top 15-20% of a model predicting a purchase from Lids. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.179	Lilly Pulitzer Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,47	28,29	This audience consists of households in the top 15-20% of a model predicting a purchase from Lilly Pulitzer. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.281	Loft Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,46	28,27	This audience consists of households in the top 15-20% of a model predicting a purchase from LOFT. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.282	Lord & Taylor Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,57	28,49	This audience consists of households in the top 15-20% of a model predicting a purchase from Lord & Taylor. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.283	Lululemon Athletica Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,57	30,60	This audience consists of households in the top 15-20% of a model predicting a purchase from Lululemon Athletica. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.181	Lulus Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,82	31,13	This audience consists of households in the top 15-20% of a model predicting a purchase from Lulus. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.284	Macy's Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,61	28,58	This audience consists of households in the top 15-20% of a model predicting a purchase from Macy's. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.327	Madewell	Brand Propensities	Apparel	Retail		Household	Modeled	15,53	32,62	This audience consists of households in the top 15-20% of a model predicting a purchase from Madewell. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.484	Marshalls Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,83	31,14	This audience consists of households in the top 15-20% of a model predicting a purchase from Marshalls. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.319	Men's Wearhouse Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,43	28,21	This audience consists of households in the top 15-20% of a model predicting a purchase from Men's Wearhouse. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.312	Merrell Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	12,54	26,34	This audience consists of households in the top 15-20% of a model predicting a purchase from Merrell. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.486	MeUndies Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	15,46	32,46	This audience consists of households in the top 15-20% of a model predicting a purchase from MeUndies. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.286	Michael Kors Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,14	27,59	This audience consists of households in the top 15-20% of a model predicting a purchase from Michael Kors. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.149	Nautica Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	11,59	24,33	This audience consists of households in the top 15-20% of a model predicting a purchase from Nautica. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.288	Neiman Marcus Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	16,37	34,37	This audience consists of households in the top 15-20% of a model predicting a purchase from Neiman Marcus. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.290	New Balance Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	15,58	32,72	This audience consists of households in the top 15-20% of a model predicting a purchase from New Balance. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.291	New York & Company Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	12,94	27,17	This audience consists of households in the top 15-20% of a model predicting a purchase from New York & Company. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.292	Nike Buyer Propensity	Brand Propensities	Apparel	Retail	Sports	Household	Modeled	14,69	30,86	This audience consists of households in the top 15-20% of a model predicting a purchase from Nike. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.331	Nobull	Brand Propensities	Apparel	Retail		Household	Modeled	13,40	28,13	This audience consists of households in the top 15-20% of a model predicting a purchase from Nobull. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.293	Nordstrom Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,58	30,62	This audience consists of households in the top 15-20% of a model predicting a purchase from Nordstrom. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.294	Nordstrom Rack Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,33	30,10	This audience consists of households in the top 15-20% of a model predicting a purchase from Nordstrom Rack. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.080	Oakley Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	12,22	25,65	This audience consists of households in the top 15-20% of a model predicting a purchase from Oakley. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.295	Old Navy Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,56	28,48	This audience consists of households in the top 15-20% of a model predicting a purchase from Old Navy. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.332	Pacific Sunwear	Brand Propensities	Apparel	Retail		Household	Modeled	14,09	29,60	This audience consists of households in the top 15-20% of a model predicting a purchase from Pacific Sunwear. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.297	Pandora Jewelry Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	15,48	32,50	This audience consists of households in the top 15-20% of a model predicting a purchase from Pandora Jewelry. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.298	Patagonia Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,05	29,51	This audience consists of households in the top 15-20% of a model predicting a purchase from Patagonia. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.301	Puma Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,23	29,89	This audience consists of households in the top 15-20% of a model predicting a purchase from Puma. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.302	Ralph Lauren Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	16,03	33,66	This audience consists of households in the top 15-20% of a model predicting a purchase from Ralph Lauren. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.303	Ray-Ban Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	15,34	32,21	This audience consists of households in the top 15-20% of a model predicting a purchase from Ray Ban. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.119	Reebok Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	16,63	34,93	This audience consists of households in the top 15-20% of a model predicting a purchase from Reebok. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.121	Rent the Runway Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	15,80	33,19	This audience consists of households in the top 15-20% of a model predicting a purchase from Rent the Runway. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.168	Ross Dress For Less Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,84	31,16	This audience consists of households in the top 15-20% of a model predicting a purchase from Ross Dress For Less. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.304	Rue La La Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,89	31,27	This audience consists of households in the top 15-20% of a model predicting a purchase from Rue La La. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.307	Saks Fifth Avenue OFF 5TH Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	15,90	33,40	This audience consists of households in the top 15-20% of a model predicting a purchase from Saks Fifth Avenue OFF 5TH. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.123	Samsonite Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,75	30,97	This audience consists of households in the top 15-20% of a model predicting a purchase from Samsonite. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.172	Saucony Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,25	27,83	This audience consists of households in the top 15-20% of a model predicting a purchase from Saucony. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.138	Shoe Carnival Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	10,77	22,63	This audience consists of households in the top 15-20% of a model predicting a purchase from Shoe Carnival. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.310	Shopbop Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	22,02	46,25	This audience consists of households in the top 15-20% of a model predicting a purchase from Shopbop. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.311	Sierra Trading Post Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	12,53	26,31	This audience consists of households in the top 15-20% of a model predicting a purchase from Sierra Trading Post. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.312	Skechers Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	12,30	25,82	This audience consists of households in the top 15-20% of a model predicting a purchase from Skechers. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.313	Soma.com Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,41	28,16	This audience consists of households in the top 15-20% of a model predicting a purchase from Soma.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.127	Spanx Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,63	28,62	This audience consists of households in the top 15-20% of a model predicting a purchase from Spanx. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.314	Steven Madden Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	19,64	41,24	This audience consists of households in the top 15-20% of a model predicting a purchase from Steven Madden. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.128	Stitch fix Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,17	29,77	This audience consists of households in the top 15-20% of a model predicting a purchase from Stitch fix. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.146	Stride Rite Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	12,00	25,20	This audience consists of households in the top 15-20% of a model predicting a purchase from Stride Rite. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.147	Sunglass Hut Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,45	28,24	This audience consists of households in the top 15-20% of a model predicting a purchase from Sunglass Hut. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.315	T.J. Maxx Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,87	31,23	This audience consists of households in the top 15-20% of a model predicting a purchase from T.J. Maxx. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.316	Talbots Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,07	27,45	This audience consists of households in the top 15-20% of a model predicting a purchase from Talbots. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.320	The North Face Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,20	27,72	This audience consists of households in the top 15-20% of a model predicting a purchase from The North face. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.539	ThirdLove Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	15,16	31,83	This audience consists of households in the top 15-20% of a model predicting a purchase from ThirdLove. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.115	Thursday Boot Co. Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	19,20	40,32	This audience consists of households in the top 15-20% of a model predicting a purchase from Thursday Boot Co. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.323	Timberland Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,20	29,81	This audience consists of households in the top 15-20% of a model predicting a purchase from Timberland. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.237	Tommy Bahama Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,13	27,58	This audience consists of households in the top 15-20% of a model predicting a purchase from Tommy Bahama. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.238	Tommy Hilfiger Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,20	29,81	This audience consists of households in the top 15-20% of a model predicting a purchase from Tommy Hilfiger. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.541	Tommy John Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,87	31,23	This audience consists of households in the top 15-20% of a model predicting a purchase from Tommy John. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.324	TOMS Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,08	27,47	This audience consists of households in the top 15-20% of a model predicting a purchase from TOMS. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.325	Tory Burch Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,55	30,56	This audience consists of households in the top 15-20% of a model predicting a purchase from Tory Burch. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.326	UGG Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	15,76	33,09	This audience consists of households in the top 15-20% of a model predicting a purchase from UGG. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.327	Under Armour Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	11,74	24,65	This audience consists of households in the top 15-20% of a model predicting a purchase from Under Armour. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.226	Uniqlo Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	15,20	31,93	This audience consists of households in the top 15-20% of a model predicting a purchase from Uniqlo. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.328	Urban Outfitters Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	16,35	34,33	This audience consists of households in the top 15-20% of a model predicting a purchase from Urban Outfitters. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.229	Vans Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,54	30,54	This audience consists of households in the top 15-20% of a model predicting a purchase from Vans. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.330	Vera Bradley Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	12,96	27,22	This audience consists of households in the top 15-20% of a model predicting a purchase from Vera Bradley. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.331	Victoria's Secret Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,91	29,22	This audience consists of households in the top 15-20% of a model predicting a purchase from Victoria's Secret. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.332	Warby Parker Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	15,16	31,84	This audience consists of households in the top 15-20% of a model predicting a purchase from Warby Parker. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.333	White House Black Market Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	14,61	30,67	This audience consists of households in the top 15-20% of a model predicting a purchase from White House Black Market. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.263	Wrangler Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	11,65	24,47	This audience consists of households in the top 15-20% of a model predicting a purchase from Wrangler. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.336	Zappos Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,69	28,75	This audience consists of households in the top 15-20% of a model predicting a purchase from Zappos. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.337	ZARA Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	15,55	32,66	This audience consists of households in the top 15-20% of a model predicting a purchase from Zara. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.266	Zumiez Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,58	28,52	This audience consists of households in the top 15-20% of a model predicting a purchase from Zumiez. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.586	Country Outfitter Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	12,73	26,74	This audience consists of households in the top 10-20% of a model predicting a purchase from Country Outfitter. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.588	Dailylook Buyer Propensity	Brand Propensities	Apparel	Professional Services		Household	Modeled	14,93	31,35	This audience consists of households in the top 10-20% of a model predicting a purchase from Dailylook. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.598	Eyemart Express Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	12,44	26,12	This audience consists of households in the top 10-20% of a model predicting a purchase from Eyemart Express. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.604	Fit2Run Buyer Propensity	Brand Propensities	Apparel	Sports		Household	Modeled	13,36	28,06	This audience consists of households in the top 10-20% of a model predicting a purchase from Fit2Run. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.610	Generation Tux Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	13,26	27,85	This audience consists of households in the top 10-20% of a model predicting a purchase from Generation Tux. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.633	La Police Gear Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	12,16	25,53	This audience consists of households in the top 10-20% of a model predicting a purchase from La Police Gear. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.657	Patriot Outfitters Buyer Propensity	Brand Propensities	Apparel	Retail		Household	Modeled	12,65	26,55	This audience consists of households in the top 10-20% of a model predicting a purchase from Patriot Outfitters. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.664	Potpourri Buyer Propensity	Brand Propensities	Apparel	Home		Household	Modeled	13,53	28,40	This audience consists of households in the top 10-20% of a model predicting a purchase from Potpourri. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.339	Advance Auto Parts Buyer Propensity	Brand Propensities	Auto	Auto		Household	Modeled	12,42	26,09	This audience consists of households in the top 15-20% of a model predicting a purchase from Advance Auto Parts. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.340	AutoNation Buyer Propensity	Brand Propensities	Auto	Auto		Household	Modeled	15,41	32,35	This audience consists of households in the top 15-20% of a model predicting a purchase from AutoNation. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.341	AutoZone Buyer Propensity	Brand Propensities	Auto	Auto		Household	Modeled	13,72	28,81	This audience consists of households in the top 15-20% of a model predicting a purchase from AutoZone. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.280	Big O tires Buyer Propensity	Brand Propensities	Auto	Auto		Household	Modeled	13,17	27,67	This audience consists of households in the top 15-20% of a model predicting a purchase from Big O tires. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.296	Budget Truck	Brand Propensities	Auto	Auto		Household	Modeled	14,42	30,29	This audience consists of households in the top 15-20% of a model predicting a purchase from Budget Truck. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.302	Carmax Buyer Propensity	Brand Propensities	Auto	Auto		Household	Modeled	13,30	27,93	This audience consists of households in the top 15-20% of a model predicting a purchase from Carmax. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.303	Carquest Buyer Propensity	Brand Propensities	Auto	Auto		Household	Modeled	11,89	24,97	This audience consists of households in the top 15-20% of a model predicting a purchase from Carquest. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.322	Discount Tire Buyer Propensity	Brand Propensities	Auto	Auto		Household	Modeled	13,00	27,29	This audience consists of households in the top 15-20% of a model predicting a purchase from Discount Tire. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.310	FasTrak	Brand Propensities	Auto	Auto		Household	Modeled	15,85	33,29	This audience consists of households in the top 15-20% of a model predicting a purchase from FasTrak. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.342	Ford Credit Buyer Propensity	Brand Propensities	Auto	Auto		Household	Modeled	10,41	21,87	This audience consists of households in the top 15-20% of a model predicting a purchase from Ford Credit. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.343	Harley-Davidson Buyer Propensity	Brand Propensities	Auto	Auto		Household	Modeled	15,72	33,02	This audience consists of households in the top 15-20% of a model predicting a purchase from Harley-Davidson. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.212	Jiffy Lube Buyer Propensity	Brand Propensities	Auto	Auto		Household	Modeled	13,12	27,55	This audience consists of households in the top 15-20% of a model predicting a purchase from Jiffy Lube. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.182	Meineke Buyer Propensity	Brand Propensities	Auto	Auto		Household	Modeled	12,86	27,01	This audience consists of households in the top 15-20% of a model predicting a purchase from Meineke. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.185	Midas Buyer Propensity	Brand Propensities	Auto	Auto		Household	Modeled	13,66	28,69	This audience consists of households in the top 15-20% of a model predicting a purchase from Midas. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.148	Napa Auto Parts Buyer Propensity	Brand Propensities	Auto	Auto		Household	Modeled	12,18	25,58	This audience consists of households in the top 15-20% of a model predicting a purchase from Napa Auto Parts. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.561	O'Reilly Auto Parts Buyer Propensity	Brand Propensities	Auto	Auto		Household	Modeled	12,41	26,06	This audience consists of households in the top 15-20% of a model predicting a purchase from O'Rielly Auto Parts. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.333	ParkMobile	Brand Propensities	Auto	Auto		Household	Modeled	14,85	31,18	This audience consists of households in the top 15-20% of a model predicting a purchase from ParkMobile. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.154	Pep Boys Buyer Propensity	Brand Propensities	Auto	Auto		Household	Modeled	14,70	30,88	This audience consists of households in the top 15-20% of a model predicting a purchase from Pep Boys. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.344	RockAuto Buyer Propensity	Brand Propensities	Auto	Auto		Household	Modeled	11,59	24,35	This audience consists of households in the top 15-20% of a model predicting a purchase from RockAuto. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.348	SunPass	Brand Propensities	Auto	Auto		Household	Modeled	13,19	27,69	This audience consists of households in the top 15-20% of a model predicting a purchase from SunPass. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.345	Tirerack.com Buyer Propensity	Brand Propensities	Auto	Auto		Household	Modeled	15,87	33,32	This audience consists of households in the top 15-20% of a model predicting a purchase from Tirerack.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.575	Caliber Collision Buyer Propensity	Brand Propensities	Auto	Auto		Household	Modeled	13,58	28,52	This audience consists of households in the top 10-20% of a model predicting a purchase from Caliber Collision. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.693	Tires Plus Buyer Propensity	Brand Propensities	Auto	Auto		Household	Modeled	13,80	28,98	This audience consists of households in the top 10-20% of a model predicting a purchase from Tires Plus. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.347	Big Lots Stores Buyer Propensity	Brand Propensities	Big Box Retail	Retail		Household	Modeled	13,61	28,57	This audience consists of households in the top 15-20% of a model predicting a purchase from Big Lots Stores. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.348	BJ's Wholesale Club Buyer Propensity	Brand Propensities	Big Box Retail	Retail		Household	Modeled	12,78	26,84	This audience consists of households in the top 15-20% of a model predicting a purchase from BJ's Wholesale Club. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.349	Costco Buyer Propensity	Brand Propensities	Big Box Retail	Retail		Household	Modeled	14,24	29,91	This audience consists of households in the top 15-20% of a model predicting a purchase from Costco. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.350	Dollar General Buyer Propensity	Brand Propensities	Big Box Retail	Retail		Household	Modeled	10,55	22,16	This audience consists of households in the top 15-20% of a model predicting a purchase from Dollar General. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.351	Dollar Tree Buyer Propensity	Brand Propensities	Big Box Retail	Retail		Household	Modeled	12,81	26,90	This audience consists of households in the top 15-20% of a model predicting a purchase from Dollar Tree. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.314	Giant Food	Brand Propensities	Big Box Retail	Retail		Household	Modeled	12,29	25,81	This audience consists of households in the top 15-20% of a model predicting a purchase from Giant Food. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.322	Hannaford	Brand Propensities	Big Box Retail	Food & Beverage		Household	Modeled	11,61	24,38	This audience consists of households in the top 15-20% of a model predicting a purchase from Hannaford. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.352	Kmart Buyer Propensity	Brand Propensities	Big Box Retail	Retail		Household	Modeled	13,35	28,03	This audience consists of households in the top 15-20% of a model predicting a purchase from Kmart. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.353	Kohl's Buyer Propensity	Brand Propensities	Big Box Retail	Retail		Household	Modeled	11,37	23,87	This audience consists of households in the top 15-20% of a model predicting a purchase from Kohl's. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.519	Office Max Buyer Propensity	Brand Propensities	Big Box Retail	Retail		Household	Modeled	13,57	28,49	This audience consists of households in the top 15-20% of a model predicting a purchase from Office Max. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.354	Sam's Club Buyer Propensity	Brand Propensities	Big Box Retail	Retail		Household	Modeled	12,00	25,21	This audience consists of households in the top 15-20% of a model predicting a purchase from Sam's Club. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.355	Sears Buyer Propensity	Brand Propensities	Big Box Retail	Retail		Household	Modeled	11,72	24,61	This audience consists of households in the top 15-20% of a model predicting a purchase from Sears. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.343	ShopRite	Brand Propensities	Big Box Retail	Retail		Household	Modeled	14,30	30,04	This audience consists of households in the top 15-20% of a model predicting a purchase from ShopRite. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.345	Sprouts Farmers Market	Brand Propensities	Big Box Retail	Food & Beverage		Household	Modeled	16,21	34,03	This audience consists of households in the top 15-20% of a model predicting a purchase from Sprouts Farmers Market. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.356	Staples Buyer Propensity	Brand Propensities	Big Box Retail	Retail		Household	Modeled	13,30	27,93	This audience consists of households in the top 15-20% of a model predicting a purchase from Staples. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.357	Target Buyer Propensity	Brand Propensities	Big Box Retail	Retail		Household	Modeled	14,38	30,19	This audience consists of households in the top 15-20% of a model predicting a purchase from Target. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.358	Walmart Buyer Propensity	Brand Propensities	Big Box Retail	Retail		Household	Modeled	11,81	24,80	This audience consists of households in the top 15-20% of a model predicting a purchase from Walmart. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.563	ALDI Buyer Propensity	Brand Propensities	Big Box Retail	Food & Beverage		Household	Modeled	12,19	25,59	This audience consists of households in the top 10-20% of a model predicting a purchase from Aldi. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.565	At Home Buyer Propensity	Brand Propensities	Big Box Retail	Food & Beverage		Household	Modeled	11,56	24,27	This audience consists of households in the top 10-20% of a model predicting a purchase from At Home. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.599	Family Dollar Stores Buyer Propensity	Brand Propensities	Big Box Retail	Retail		Household	Modeled	13,00	27,30	This audience consists of households in the top 10-20% of a model predicting a purchase from Family Dollar Stores. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.123	Amazon Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Retail		Household	Modeled	12,17	25,56	This audience consists of households in the top 15-20% of a model predicting big spenders from Amazon. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.124	American Eagle Outfitters Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Retail		Household	Modeled	14,11	29,63	This audience consists of households in the top 15-20% of a model predicting big spenders from American Eagle Outfitters. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.125	Blue Apron Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Food & Beverage		Household	Modeled	14,47	30,39	This audience consists of households in the top 15-20% of a model predicting big spenders from Blue Apron. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.126	Chewy.com Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Pet	Retail	Household	Modeled	14,46	30,36	This audience consists of households in the top 15-20% of a model predicting big spenders from Chewy.com. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.127	Clinique Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Health & Beauty	Retail	Household	Modeled	13,09	27,49	This audience consists of households in the top 15-20% of a model predicting big spenders from Clinique. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.128	Coach Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Retail		Household	Modeled	13,77	28,91	This audience consists of households in the top 15-20% of a model predicting big spenders from Coach. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.129	Costco Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Retail	Food & Beverage	Household	Modeled	12,57	26,39	This audience consists of households in the top 15-20% of a model predicting big spenders from Costco. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.130	Disney Resorts Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Travel		Household	Modeled	12,50	26,25	This audience consists of households in the top 15-20% of a model predicting big spenders from Disney Resorts. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.131	DoorDash Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Food & Beverage		Household	Modeled	14,25	29,93	This audience consists of households in the top 15-20% of a model predicting big spenders from DoorDash. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.132	DraftKings Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Media & Entertainment		Household	Modeled	12,52	26,29	This audience consists of households in the top 15-20% of a model predicting big spenders from DraftKings. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.133	Eddie Bauer Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Retail		Household	Modeled	13,42	28,19	This audience consists of households in the top 15-20% of a model predicting big spenders from Eddie Bauer. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.134	Gap Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Retail		Household	Modeled	14,25	29,93	This audience consists of households in the top 15-20% of a model predicting big spenders from GAP. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
228.130	Grubhub Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Food & Beverage		Household	Modeled	14,92	31,32	This audience consists of households in the top 15-20% of a model predicting big spenders from GrubHub. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.136	Lyft Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Travel		Household	Modeled	15,32	32,17	This audience consists of households in the top 15-20% of a model predicting big spenders from Lyft. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.137	Macy's Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Retail		Household	Modeled	12,10	25,41	This audience consists of households in the top 15-20% of a model predicting big spenders from Macy's. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.138	MGM Grand Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Media & Entertainment	Travel	Household	Modeled	13,93	29,26	This audience consists of households in the top 15-20% of a model predicting big spenders from MGM Grand. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.139	Michael Kors Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Retail		Household	Modeled	14,44	30,32	This audience consists of households in the top 15-20% of a model predicting big spenders from Michael Kors. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.140	Old Navy Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Retail		Household	Modeled	14,53	30,52	This audience consists of households in the top 15-20% of a model predicting big spenders from Old Navy. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.141	Saks Fifth Avenue Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Retail		Household	Modeled	15,37	32,27	This audience consists of households in the top 15-20% of a model predicting big spenders from Saks Fifth Avenue. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.142	Sam's Club Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Food & Beverage		Household	Modeled	12,00	25,19	This audience consists of households in the top 15-20% of a model predicting big spenders from Sam's Club. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.143	Sephora Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Health & Beauty	Retail	Household	Modeled	16,27	34,16	This audience consists of households in the top 15-20% of a model predicting big spenders from Sephora. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.144	Stamps.com Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Professional Services		Household	Modeled	17,79	37,37	This audience consists of households in the top 15-20% of a model predicting big spenders from Stamps.com. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.145	Tiffany Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Retail		Household	Modeled	14,58	30,62	This audience consists of households in the top 15-20% of a model predicting big spenders from Tiffany. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.146	Ulta Beauty Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Health & Beauty	Retail	Household	Modeled	13,92	29,23	This audience consists of households in the top 15-20% of a model predicting big spenders from Ulta Beauty. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.147	USPS Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Professional Services		Household	Modeled	20,31	42,65	This audience consists of households in the top 15-20% of a model predicting big spenders from USPS. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.148	Walmart Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Retail		Household	Modeled	12,33	25,90	This audience consists of households in the top 15-20% of a model predicting big spenders from Walmart. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.149	Warby Parker Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Retail		Household	Modeled	15,20	31,93	This audience consists of households in the top 15-20% of a model predicting big spenders from Warby Parker. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.150	Wayfair Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Retail		Household	Modeled	13,48	28,31	This audience consists of households in the top 15-20% of a model predicting big spenders from Wayfair. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.151	Wingstop Big Spender Propensity	Brand Propensities	Big Spenders by Brand	QSR	Food & Beverage	Household	Modeled	13,12	27,56	This audience consists of households in the top 15-20% of a model predicting big spenders from Wingstop. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.152	Zara Big Spender Propensity	Brand Propensities	Big Spenders by Brand	Retail		Household	Modeled	15,87	33,32	This audience consists of households in the top 15-20% of a model predicting big spenders from Zara. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.167	Active Wear Big Spender Propensity	Brand Propensities	Big Spenders by Brand Category	Retail		Household	Modeled	14,22	29,87	This audience consists of households in the top 15-20% of a model predicting big spenders within the Active Wear category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.096	Airlines Big Spender Propensity	Brand Propensities	Big Spenders by Brand Category	Travel		Household	Modeled	13,48	28,30	This audience consists of households in the top 15-20% of a model predicting big spenders within the Airlines category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.097	Apparel Accessories Big Spender Propensity	Brand Propensities	Big Spenders by Brand Category	Retail		Household	Modeled	14,30	30,02	This audience consists of households in the top 15-20% of a model predicting big spenders within the Apparel Accessories category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.122	Auto Insurance Big Spender Propensity	Brand Propensities	Big Spenders by Brand Category	Auto		Household	Modeled	10,57	22,20	This audience consists of households in the top 15-20% of a model predicting big spenders within the Auto Insurance category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.098	Cruise Lines Big Spender Propensity	Brand Propensities	Big Spenders by Brand Category	Travel		Household	Modeled	14,36	30,15	This audience consists of households in the top 15-20% of a model predicting big spenders within the Cruise Lines category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.099	Delivery Aggregators Big Spender Propensity	Brand Propensities	Big Spenders by Brand Category	Home		Household	Modeled	14,52	30,49	This audience consists of households in the top 15-20% of a model predicting big spenders within the Delivery Aggregators category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.100	Drug Store Big Spender Propensity	Brand Propensities	Big Spenders by Brand Category	Retail	Food & Beverage	Household	Modeled	12,29	25,81	This audience consists of households in the top 15-20% of a model predicting big spenders within the Drug/Pharma category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.101	Electronics Big Spender Propensity	Brand Propensities	Big Spenders by Brand Category	Retail	Tech	Household	Modeled	11,60	24,37	This audience consists of households in the top 15-20% of a model predicting big spenders within the Electronics category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.102	Fitness Center Big Spender Propensity	Brand Propensities	Big Spenders by Brand Category	Health & Beauty		Household	Modeled	12,68	26,64	This audience consists of households in the top 15-20% of a model predicting big spenders within the Fitness Centers category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.103	Hardware Stores Big Spender Propensity	Brand Propensities	Big Spenders by Brand Category	Retail	Home	Household	Modeled	13,98	29,36	This audience consists of households in the top 15-20% of a model predicting big spenders within the Hardware Stores category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.104	Health Care Big Spender Propensity	Brand Propensities	Big Spenders by Brand Category	Health & Beauty		Household	Modeled	14,25	29,93	This audience consists of households in the top 15-20% of a model predicting big spenders within the Healthcare category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.105	Home Furnishings Big Spender Propensity	Brand Propensities	Big Spenders by Brand Category	Home	Retail	Household	Modeled	13,33	28,00	This audience consists of households in the top 15-20% of a model predicting big spenders within the Home Furnishing category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.106	Home Improvement Big Spender Propensity	Brand Propensities	Big Spenders by Brand Category	Home	Retail	Household	Modeled	11,38	23,90	This audience consists of households in the top 15-20% of a model predicting big spenders within the Home Improvements category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.107	Home Security Big Spender Propensity	Brand Propensities	Big Spenders by Brand Category	Home	Tech	Household	Modeled	13,95	29,29	This audience consists of households in the top 15-20% of a model predicting big spenders within the Home Security category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.108	Intimate Apparel Big Spender Propensity	Brand Propensities	Big Spenders by Brand Category	Retail		Household	Modeled	14,35	30,14	This audience consists of households in the top 15-20% of a model predicting big spenders within the Intimate Apparel category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.109	Jewelry Watches Big Spender Propensity	Brand Propensities	Big Spenders by Brand Category	Retail		Household	Modeled	14,82	31,13	This audience consists of households in the top 15-20% of a model predicting big spenders within the Jewelry/Watches category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.110	Lodging Big Spender Propensity	Brand Propensities	Big Spenders by Brand Category	Travel		Household	Modeled	12,39	26,02	This audience consists of households in the top 15-20% of a model predicting big spenders within the Lodging category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.111	Meal Kits Big Spender Propensity	Brand Propensities	Big Spenders by Brand Category	Food & Beverage		Household	Modeled	18,19	38,20	This audience consists of households in the top 15-20% of a model predicting big spenders within the Meal Kits category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.112	Mobile Big Spender Propensity	Brand Propensities	Big Spenders by Brand Category	Telecom		Household	Modeled	11,44	24,03	This audience consists of households in the top 15-20% of a model predicting big spenders within the Mobile category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.113	Occasion Gifts Big Spender Propensity	Brand Propensities	Big Spenders by Brand Category	Retail		Household	Modeled	10,50	22,06	This audience consists of households in the top 15-20% of a model predicting big spenders within the Occasion Gifts category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.114	Online Grocers Big Spender Propensity	Brand Propensities	Big Spenders by Brand Category	Food & Beverage	Retail	Household	Modeled	15,50	32,54	This audience consists of households in the top 15-20% of a model predicting big spenders within the Online Grocers category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.115	QSR Big Spender Propensity	Brand Propensities	Big Spenders by Brand Category	Food & Beverage		Household	Modeled	11,90	24,99	This audience consists of households in the top 15-20% of a model predicting big spenders within the QSR category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.116	Rental Cars Big Spender Propensity	Brand Propensities	Big Spenders by Brand Category	Travel		Household	Modeled	12,98	27,25	This audience consists of households in the top 15-20% of a model predicting big spenders within the Rental Cars category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.117	Sporting Goods Big Spender Propensity	Brand Propensities	Big Spenders by Brand Category	Retail	Sports	Household	Modeled	11,23	23,58	This audience consists of households in the top 15-20% of a model predicting big spenders within the Sporting Goods category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.118	Supermarkets Big Spender Propensity	Brand Propensities	Big Spenders by Brand Category	Food & Beverage		Household	Modeled	12,21	25,64	This audience consists of households in the top 15-20% of a model predicting big spenders within the Super Markets category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.119	Ticket Agencies Big Spender Propensity	Brand Propensities	Big Spenders by Brand Category	Media & Entertainment		Household	Modeled	12,39	26,02	This audience consists of households in the top 15-20% of a model predicting big spenders within the Ticket Agencies category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.120	Travel Agencies Big Spender Propensity	Brand Propensities	Big Spenders by Brand Category	Travel		Household	Modeled	12,98	27,25	This audience consists of households in the top 15-20% of a model predicting big spenders within the Travel Agencies category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.153	AT&T Mobile Switcher Propensity	Brand Propensities	Brand/Category Switchers	Telecom		Household	Modeled	10,86	22,81	This audience consists of households in the top 15-20% of a model predicting mobile plan switchers from AT&T. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.154	Boost Mobile Switcher Propensity	Brand Propensities	Brand/Category Switchers	Telecom		Household	Modeled	9,23	19,38	This audience consists of households in the top 15-20% of a model predicting mobile plan switchers from Boost Mobile. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.155	LG Mobile Switcher Propensity	Brand Propensities	Brand/Category Switchers	Telecom		Household	Modeled	9,85	20,68	This audience consists of households in the top 15-20% of a model predicting mobile plan switchers from LG. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.156	MetroPCS Mobile Switcher Propensity	Brand Propensities	Brand/Category Switchers	Telecom		Household	Modeled	12,81	26,89	This audience consists of households in the top 15-20% of a model predicting mobile plan switchers from Metro PCS. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.157	Sprint Mobile Switcher Propensity	Brand Propensities	Brand/Category Switchers	Telecom		Household	Modeled	10,73	22,53	This audience consists of households in the top 15-20% of a model predicting mobile plan switchers from Sprint. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.158	T-Mobile Switcher Propensity	Brand Propensities	Brand/Category Switchers	Telecom		Household	Modeled	14,64	30,75	This audience consists of households in the top 15-20% of a model predicting mobile plan switchers from T-Mobile. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.159	Verizon Mobile Switcher Propensity	Brand Propensities	Brand/Category Switchers	Telecom		Household	Modeled	15,09	31,69	This audience consists of households in the top 15-20% of a model predicting mobile plan switchers from Verizon. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.166	Propensity to Switch from Allstate Insurance	Brand Propensities	Brand/Category Switchers	Financial Services		Household	Modeled	13,57	28,49	This audience consists of households in the top 15-20% of a model predicting auto insurance switchers from Allstate Insurance. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.165	Propensity to Switch from Farmers Insurance	Brand Propensities	Brand/Category Switchers	Financial Services		Household	Modeled	11,59	24,35	This audience consists of households in the top 15-20% of a model predicting auto insurance switchers from Farmers Insurance. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.164	Propensity to Switch from Geico Insurance	Brand Propensities	Brand/Category Switchers	Financial Services		Household	Modeled	13,05	27,41	This audience consists of households in the top 15-20% of a model predicting auto insurance switchers from Geico Insurance. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.163	Propensity to Switch from Progressive Insurance	Brand Propensities	Brand/Category Switchers	Financial Services		Household	Modeled	11,12	23,35	This audience consists of households in the top 15-20% of a model predicting auto insurance switchers from Progressive Insurance. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.162	Propensity to Switch from Safeco Insurance	Brand Propensities	Brand/Category Switchers	Financial Services		Household	Modeled	12,42	26,07	This audience consists of households in the top 15-20% of a model predicting auto insurance switchers from Safeco Insurance. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.161	Propensity to Switch from State Farm Insurance	Brand Propensities	Brand/Category Switchers	Financial Services		Household	Modeled	11,05	23,21	This audience consists of households in the top 15-20% of a model predicting auto insurance switchers from State Farm Insurance. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.160	Propensity to Switch from Travelers Insurance	Brand Propensities	Brand/Category Switchers	Financial Services		Household	Modeled	12,74	26,76	This audience consists of households in the top 15-20% of a model predicting auto insurance switchers from Travelers Insurance. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.589	Dashlane Buyer Propensity	Brand Propensities	Computer & Electronics	Tech		Household	Modeled	15,00	31,49	This audience consists of households in the top 10-20% of a model predicting a purchase from Dashlane. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.590	Datacamp Buyer Propensity	Brand Propensities	Computer & Electronics	Tech		Household	Modeled	15,00	31,51	This audience consists of households in the top 10-20% of a model predicting a purchase from Datacamp. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.596	Envato Buyer Propensity	Brand Propensities	Computer & Electronics	Tech		Household	Modeled	16,48	34,60	This audience consists of households in the top 10-20% of a model predicting a purchase from Envato. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.619	Hellotech Buyer Propensity	Brand Propensities	Computer & Electronics	Tech		Household	Modeled	15,28	32,09	This audience consists of households in the top 10-20% of a model predicting a purchase from Hellotech. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.638	Malwarebytes Buyer Propensity	Brand Propensities	Computer & Electronics	Tech		Household	Modeled	13,57	28,49	This audience consists of households in the top 10-20% of a model predicting a purchase from Malwarebytes. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.192	BP Buyer Propensity	Brand Propensities	Convenience & Gas	Oil & Gas		Household	Modeled	13,72	28,82	This audience consists of households in the top 15-20% of a model predicting a purchase from BP. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.163	Circle K Buyer Propensity	Brand Propensities	Convenience & Gas	Oil & Gas		Household	Modeled	12,89	27,07	This audience consists of households in the top 15-20% of a model predicting a purchase from Circle K. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.164	Citgo Buyer Propensity	Brand Propensities	Convenience & Gas	Oil & Gas		Household	Modeled	13,43	28,20	This audience consists of households in the top 15-20% of a model predicting a purchase from Citgo. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.358	Convenience & Gas	Brand Propensities	Convenience & Gas	Oil & Gas		Household	Modeled	14,81	31,11	This audience consists of households in the top 15-20% of a model predicting a purchase from the Convenience & Gas category. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.132	Cumberland Farms Buyer Propensity	Brand Propensities	Convenience & Gas	Oil & Gas		Household	Modeled	12,16	25,54	This audience consists of households in the top 15-20% of a model predicting a purchase from Cumberland Farms. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.306	Marathon Petroleum Buyer Propensity	Brand Propensities	Convenience & Gas	Oil & Gas		Household	Modeled	13,24	27,81	This audience consists of households in the top 15-20% of a model predicting a purchase from Marathon Petroleum. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.232	Wawa Buyer Propensity	Brand Propensities	Convenience & Gas	Food & Beverage	Oil & Gas	Household	Modeled	13,95	29,30	This audience consists of households in the top 15-20% of a model predicting a purchase from Wawa. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.667	Printify Buyer Propensity	Brand Propensities	Convenience & Gas	Professional Services		Household	Modeled	15,18	31,87	This audience consists of households in the top 10-20% of a model predicting a purchase from Printify. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.360	Crest Buyer Propensity	Brand Propensities	CPG	CPG		Household	Modeled	13,77	28,92	This audience consists of households in the top 15-20% of a model predicting a purchase from Crest. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.362	Kraft Buyer Propensity	Brand Propensities	CPG	CPG		Household	Modeled	13,09	27,50	This audience consists of households in the top 15-20% of a model predicting a purchase from Kraft. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.363	L'oreal Buyer Propensity	Brand Propensities	CPG	CPG		Household	Modeled	18,35	38,53	This audience consists of households in the top 15-20% of a model predicting a purchase from L'oreal. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.194	Bumble Buyer Propensity	Brand Propensities	Dating App	Media & Entertainment		Household	Modeled	14,43	30,30	This audience consists of households in the top 15-20% of a model predicting a purchase from Bumble. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.650	Match.com Buyer Propensity	Brand Propensities	Dating App	Media & Entertainment		Household	Modeled	15,67	32,92	This audience consists of households in the top 15-20% of a model predicting a purchase from Match.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.081	OkCupid Buyer Propensity	Brand Propensities	Dating App	Media & Entertainment		Household	Modeled	20,50	43,06	This audience consists of households in the top 15-20% of a model predicting a purchase from OkCupid. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.692	Tinder Buyer Propensity	Brand Propensities	Dating App	Media & Entertainment		Household	Modeled	14,05	29,50	This audience consists of households in the top 10-20% of a model predicting a purchase from Tinder. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.365	1-800-Flowers Buyer Propensity	Brand Propensities	Ecommerce	Retail		Household	Modeled	14,54	30,54	This audience consists of households in the top 15-20% of a model predicting a purchase from 1-800-Flowers. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.290	AliExpress	Brand Propensities	Ecommerce	Retail		Household	Modeled	14,78	31,04	This audience consists of households in the top 15-20% of a model predicting a purchase from AliExpress. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.367	Amazon Buyer Propensity	Brand Propensities	Ecommerce	Retail		Household	Modeled	14,20	29,81	This audience consists of households in the top 15-20% of a model predicting a purchase from Amazon. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.130	Craigslist Buyer Propensity	Brand Propensities	Ecommerce	Retail		Household	Modeled	12,38	25,99	This audience consists of households in the top 15-20% of a model predicting a purchase from Craigslist. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.376	delivery.com Buyer Propensity	Brand Propensities	Ecommerce	Retail		Household	Modeled	14,87	31,23	This audience consists of households in the top 15-20% of a model predicting a purchase from delivery.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.379	Ebay Buyer Propensity	Brand Propensities	Ecommerce	Retail		Household	Modeled	12,48	26,22	This audience consists of households in the top 15-20% of a model predicting a purchase from Ebay. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.381	Etsy.com Buyer Propensity	Brand Propensities	Ecommerce	Retail		Household	Modeled	14,29	30,01	This audience consists of households in the top 15-20% of a model predicting a purchase from Etsy.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.385	Go Daddy Buyer Propensity	Brand Propensities	Ecommerce	Retail		Household	Modeled	15,20	31,93	This audience consists of households in the top 15-20% of a model predicting a purchase from Go Daddy. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.386	Google Wallet Buyer Propensity	Brand Propensities	Ecommerce	Retail		Household	Modeled	20,95	44,00	This audience consists of households in the top 15-20% of a model predicting a purchase from Google Wallet. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.388	Groupon Buyer Propensity	Brand Propensities	Ecommerce	Retail		Household	Modeled	15,44	32,43	This audience consists of households in the top 15-20% of a model predicting a purchase from Groupon. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.390	HSN Buyer Propensity	Brand Propensities	Ecommerce	Retail		Household	Modeled	12,63	26,53	This audience consists of households in the top 15-20% of a model predicting a purchase from HSN. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.391	Jet.com Buyer Propensity	Brand Propensities	Ecommerce	Retail		Household	Modeled	15,21	31,94	This audience consists of households in the top 15-20% of a model predicting a purchase from Jet.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.392	Jo-Ann Buyer Propensity	Brand Propensities	Ecommerce	Retail		Household	Modeled	12,90	27,09	This audience consists of households in the top 15-20% of a model predicting a purchase from Jo-Ann. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.393	LinkedIn Buyer Propensity	Brand Propensities	Ecommerce	Retail		Household	Modeled	15,41	32,37	This audience consists of households in the top 15-20% of a model predicting a purchase from LinkedIn. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.394	Meijer Buyer Propensity	Brand Propensities	Ecommerce	Retail		Household	Modeled	11,33	23,80	This audience consists of households in the top 15-20% of a model predicting a purchase from Meijer. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.311	Mercari Buyer Propensity	Brand Propensities	Ecommerce	Retail		Household	Modeled	14,28	29,99	This audience consists of households in the top 15-20% of a model predicting a purchase from Mercari. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.396	Office Depot Buyer Propensity	Brand Propensities	Ecommerce	Retail		Household	Modeled	14,76	31,01	This audience consists of households in the top 15-20% of a model predicting a purchase from Office Depot. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.397	Overstock.com Buyer Propensity	Brand Propensities	Ecommerce	Retail		Household	Modeled	13,91	29,20	This audience consists of households in the top 15-20% of a model predicting a purchase from Overstock.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.399	ProFlowers Buyer Propensity	Brand Propensities	Ecommerce	Retail		Household	Modeled	13,47	28,30	This audience consists of households in the top 15-20% of a model predicting a purchase from ProFlowers. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.402	QVC Buyer Propensity	Brand Propensities	Ecommerce	Retail		Household	Modeled	12,75	26,78	This audience consists of households in the top 15-20% of a model predicting a purchase from QVC. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.407	Shopify Buyer Propensity	Brand Propensities	Ecommerce	Retail		Household	Modeled	14,15	29,72	This audience consists of households in the top 15-20% of a model predicting a purchase from Shopify. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.410	Snapfish Buyer Propensity	Brand Propensities	Ecommerce	Retail		Household	Modeled	13,10	27,50	This audience consists of households in the top 15-20% of a model predicting a purchase from Snapfish. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.414	Tiny Prints Buyer Propensity	Brand Propensities	Ecommerce	Retail		Household	Modeled	11,88	24,95	This audience consists of households in the top 15-20% of a model predicting a purchase from Tiny Prints. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.415	USPS Buyer Propensity	Brand Propensities	Ecommerce	Retail		Household	Modeled	17,33	36,39	This audience consists of households in the top 15-20% of a model predicting a purchase from USPS. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.418	Zulily Buyer Propensity	Brand Propensities	Ecommerce	Retail		Household	Modeled	12,67	26,61	This audience consists of households in the top 15-20% of a model predicting a purchase from Zulily. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.346	StockX	Brand Propensities	Ecommerce	Retail		Household	Modeled	14,39	30,23	This audience consists of households in the top 15-20% of a model predicting a purchase from StockX. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.293	Babbel.com	Brand Propensities	Education			Household	Modeled	15,29	32,11	This audience consists of households in the top 15-20% of a model predicting a purchase from Babbel.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.568	Bartleby Buyer Propensity	Brand Propensities	Education	Education		Household	Modeled	12,89	27,07	This audience consists of households in the top 10-20% of a model predicting a purchase from Bartleby. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.644	Mathway Buyer Propensity	Brand Propensities	Education	Tech		Household	Modeled	13,57	28,49	This audience consists of households in the top 10-20% of a model predicting a purchase from Mathway. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.663	Pluralsight Buyer Propensity	Brand Propensities	Education	Tech		Household	Modeled	14,50	30,45	This audience consists of households in the top 10-20% of a model predicting a purchase from Pluralsight. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.697	Udemy Buyer Propensity	Brand Propensities	Education	Education		Household	Modeled	15,06	31,62	This audience consists of households in the top 10-20% of a model predicting a purchase from Udemy. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.705	Wyzant Buyer Propensity	Brand Propensities	Education	Education		Household	Modeled	14,80	31,08	This audience consists of households in the top 10-20% of a model predicting a purchase from Wyzant. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.288	ABT Electronics	Brand Propensities	Electronics	Tech		Household	Modeled	13,43	28,20	This audience consists of households in the top 15-20% of a model predicting a purchase from ABT Electronics. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.422	Adobe Buyer Propensity	Brand Propensities	Electronics	Tech	Media & Entertainment	Household	Modeled	15,42	32,37	This audience consists of households in the top 15-20% of a model predicting a purchase from Adobe. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.424	Apple Buyer Propensity	Brand Propensities	Electronics	Tech	Retail	Household	Modeled	15,33	32,18	This audience consists of households in the top 15-20% of a model predicting a purchase from Apple. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.428	B&H Photo Video Buyer Propensity	Brand Propensities	Electronics	Tech	Retail	Household	Modeled	13,70	28,77	This audience consists of households in the top 15-20% of a model predicting a purchase from B&H Photo Video. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.427	Best Buy Buyer Propensity	Brand Propensities	Electronics	Retail	Tech	Household	Modeled	13,76	28,90	This audience consists of households in the top 15-20% of a model predicting a purchase from Best Buy. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.429	Bose Buyer Propensity	Brand Propensities	Electronics	Tech	Retail	Household	Modeled	13,37	28,07	This audience consists of households in the top 15-20% of a model predicting a purchase from Bose. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.432	Crutchfield Buyer Propensity	Brand Propensities	Electronics	Retail	Tech	Household	Modeled	8,76	18,40	This audience consists of households in the top 15-20% of a model predicting a purchase from Crutchfield. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.434	Dell Buyer Propensity	Brand Propensities	Electronics	Tech	Retail	Household	Modeled	13,00	27,30	This audience consists of households in the top 15-20% of a model predicting a purchase from Dell. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.437	Garmin Buyer Propensity	Brand Propensities	Electronics	Tech		Household	Modeled	12,81	26,90	This audience consists of households in the top 15-20% of a model predicting a purchase from Garmin. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.438	Geek Squad Buyer Propensity	Brand Propensities	Electronics	Tech		Household	Modeled	11,57	24,30	This audience consists of households in the top 15-20% of a model predicting a purchase from Geek Squad. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.439	GoPro Buyer Propensity	Brand Propensities	Electronics	Tech	Media & Entertainment	Household	Modeled	13,83	29,04	This audience consists of households in the top 15-20% of a model predicting a purchase from GoPro. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.246	GreatCall Buyer Propensity	Brand Propensities	Electronics	Tech		Household	Modeled	7,79	16,36	This audience consists of households in the top 15-20% of a model predicting a purchase from GreatCall. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.440	HP Buyer Propensity	Brand Propensities	Electronics	Tech		Household	Modeled	12,15	25,52	This audience consists of households in the top 15-20% of a model predicting a purchase from HP. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.271	iRobot Buyer Propensity	Brand Propensities	Electronics	Tech		Household	Modeled	13,49	28,34	This audience consists of households in the top 15-20% of a model predicting a purchase from iRobot. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.445	Lenovo Buyer Propensity	Brand Propensities	Electronics	Tech	Media & Entertainment	Household	Modeled	13,67	28,71	This audience consists of households in the top 15-20% of a model predicting a purchase from Lenovo. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.444	LG Buyer Propensity	Brand Propensities	Electronics	Tech		Household	Modeled	14,26	29,94	This audience consists of households in the top 15-20% of a model predicting a purchase from LG. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.446	Microsoft Buyer Propensity	Brand Propensities	Electronics	Tech	Media & Entertainment	Household	Modeled	13,20	27,72	This audience consists of households in the top 15-20% of a model predicting a purchase from Microsoft. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.447	Microsoft Store Buyer Propensity	Brand Propensities	Electronics	Retail	Tech	Household	Modeled	17,53	36,82	This audience consists of households in the top 15-20% of a model predicting a purchase from Microsoft Store. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.450	Motorola Buyer Propensity	Brand Propensities	Electronics	Tech	Telecom	Household	Modeled	19,23	40,39	This audience consists of households in the top 15-20% of a model predicting a purchase from Motorola. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.452	Norton Buyer Propensity	Brand Propensities	Electronics	Tech		Household	Modeled	13,64	28,64	This audience consists of households in the top 15-20% of a model predicting a purchase from Norton. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.454	Otterbox Buyer Propensity	Brand Propensities	Electronics	Tech		Household	Modeled	19,43	40,79	This audience consists of households in the top 15-20% of a model predicting a purchase from Otterbox. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.456	P.C. Richard & Son Buyer Propensity	Brand Propensities	Electronics	Retail	Home	Household	Modeled	15,70	32,97	This audience consists of households in the top 15-20% of a model predicting a purchase from P.C. Richard and Son. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.457	RadioShack Buyer Propensity	Brand Propensities	Electronics	Tech		Household	Modeled	18,30	38,44	This audience consists of households in the top 15-20% of a model predicting a purchase from RadioShack. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.460	Skype Buyer Propensity	Brand Propensities	Electronics	Tech	Telecom	Household	Modeled	14,23	29,88	This audience consists of households in the top 15-20% of a model predicting a purchase from Skype. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.143	Sonos Buyer Propensity	Brand Propensities	Electronics	Tech		Household	Modeled	14,82	31,13	This audience consists of households in the top 15-20% of a model predicting a purchase from Sonos. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.461	Sony Buyer Propensity	Brand Propensities	Electronics	Tech	Media & Entertainment	Household	Modeled	15,06	31,63	This audience consists of households in the top 15-20% of a model predicting a purchase from Sony. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.465	Toshiba Buyer Propensity	Brand Propensities	Electronics	Tech		Household	Modeled	11,52	24,19	This audience consists of households in the top 15-20% of a model predicting a purchase from Toshiba. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.594	Eero Buyer Propensity	Brand Propensities	Electronics	Tech		Household	Modeled	13,83	29,03	This audience consists of households in the top 10-20% of a model predicting a purchase from Eero. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.650	Nanit Buyer Propensity	Brand Propensities	Electronics	Retail		Household	Modeled	13,63	28,62	This audience consists of households in the top 10-20% of a model predicting a purchase from Nanit. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.468	American Express Buyer Propensity	Brand Propensities	Financial	Financial Services		Household	Modeled	13,82	29,02	This audience consists of households in the top 15-20% of a model predicting a purchase from American Express. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.166	Coinbase Buyer Propensity	Brand Propensities	Financial	Financial Services		Household	Modeled	14,91	31,31	This audience consists of households in the top 15-20% of a model predicting a purchase from Coinbase. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.307	Experian	Brand Propensities	Financial	Financial Services		Household	Modeled	14,78	31,04	This audience consists of households in the top 15-20% of a model predicting a purchase from Experian. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.476	H&R Block Buyer Propensity	Brand Propensities	Financial	Financial Services		Household	Modeled	11,94	25,07	This audience consists of households in the top 15-20% of a model predicting a purchase from H&R Block. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.469	Intuit Buyer Propensity	Brand Propensities	Financial	Financial Services		Household	Modeled	12,12	25,45	This audience consists of households in the top 15-20% of a model predicting a purchase from Intuit. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.292	LifeLock Buyer Propensity	Brand Propensities	Financial	Financial Services		Household	Modeled	12,59	26,45	This audience consists of households in the top 15-20% of a model predicting a purchase from LifeLock. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.477	PayPal Buyer Propensity	Brand Propensities	Financial	Financial Services		Household	Modeled	14,94	31,38	This audience consists of households in the top 15-20% of a model predicting a purchase from PayPal. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.201	Raise.com Buyer Propensity	Brand Propensities	Financial	Financial Services		Household	Modeled	13,69	28,74	This audience consists of households in the top 15-20% of a model predicting a purchase from Raise.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.342	Sezzle	Brand Propensities	Financial	Financial Services		Household	Modeled	11,32	23,77	This audience consists of households in the top 15-20% of a model predicting a purchase from Sezzle. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.363	Tax Preparation	Brand Propensities	Financial	Financial Services		Household	Modeled	13,36	28,05	This audience consists of households in the top 15-20% of a model predicting a purchase from the Tax Preparation category. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.473	Western Union Buyer Propensity	Brand Propensities	Financial	Financial Services		Household	Modeled	13,66	28,69	This audience consists of households in the top 15-20% of a model predicting a purchase from Western Union. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.475	Xoom Buyer Propensity	Brand Propensities	Financial	Financial Services		Household	Modeled	14,47	30,39	This audience consists of households in the top 15-20% of a model predicting a purchase from Xoom. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.578	Canopy Buyer Propensity	Brand Propensities	Financial	Tech		Household	Modeled	14,63	30,72	This audience consists of households in the top 10-20% of a model predicting a purchase from Canopy. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.608	Freshbooks Buyer Propensity	Brand Propensities	Financial	Tech		Household	Modeled	13,97	29,33	This audience consists of households in the top 10-20% of a model predicting a purchase from Freshbooks. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.073	7-Eleven Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	15,69	32,96	This audience consists of households in the top 15-20% of a model predicting a purchase from 7-Eleven. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.473	Acme Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	14,68	30,84	This audience consists of households in the top 15-20% of a model predicting a purchase from Acme. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.475	Albertsons Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	15,30	32,13	This audience consists of households in the top 15-20% of a model predicting a purchase from Albertsons. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.482	Blue Apron Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	15,77	33,11	This audience consists of households in the top 15-20% of a model predicting a purchase from Blue Apron. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.484	Caviar Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	21,78	45,74	This audience consists of households in the top 15-20% of a model predicting a purchase from Caviar. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.298	Cold Stone Creamery	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	14,70	30,87	This audience consists of households in the top 15-20% of a model predicting a purchase from Cold Stone Creamery. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.479	CVS Buyer Propensity	Brand Propensities	Food & Drugstore	Retail	Health & Beauty	Household	Modeled	12,38	25,99	This audience consists of households in the top 15-20% of a model predicting a purchase from CVS. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.487	DAVIDsTEA Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	15,68	32,93	This audience consists of households in the top 15-20% of a model predicting a purchase from DAVIDsTEA. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.489	DoorDash Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	14,42	30,29	This audience consists of households in the top 15-20% of a model predicting a purchase from DoorDash. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.490	Drugstore.com Buyer Propensity	Brand Propensities	Food & Drugstore	Retail	Health & Beauty	Household	Modeled	8,75	18,38	This audience consists of households in the top 15-20% of a model predicting a purchase from Drugstore.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.101	Duane Reade Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	17,47	36,68	This audience consists of households in the top 15-20% of a model predicting a purchase from Duane Reade. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.491	Eat24 Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	17,73	37,24	This audience consists of households in the top 15-20% of a model predicting a purchase from Eat24. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.216	Five Below Buyer Propensity	Brand Propensities	Food & Drugstore	Retail		Household	Modeled	12,29	25,80	This audience consists of households in the top 15-20% of a model predicting a purchase from Five Below. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.506	Food Lion Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	10,92	22,94	This audience consists of households in the top 15-20% of a model predicting a purchase from Food Lion. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.492	Fresh Direct Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage	Health & Beauty	Household	Modeled	15,27	32,08	This audience consists of households in the top 15-20% of a model predicting a purchase from Fresh Direct. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.508	Freshly Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage	Health & Beauty	Household	Modeled	13,71	28,78	This audience consists of households in the top 15-20% of a model predicting a purchase from Freshly. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.493	GNC Buyer Propensity	Brand Propensities	Food & Drugstore	Retail	Health & Beauty	Household	Modeled	13,93	29,25	This audience consists of households in the top 15-20% of a model predicting a purchase from GNC. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.494	Godiva Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	14,86	31,20	This audience consists of households in the top 15-20% of a model predicting a purchase from Godiva. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.495	Grubhub Buyer Propensity	Brand Propensities	Food & Drugstore	QSR	Food & Beverage	Household	Modeled	14,39	30,22	This audience consists of households in the top 15-20% of a model predicting a purchase from Grubhub. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.496	Harry & David Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	13,25	27,82	This audience consists of households in the top 15-20% of a model predicting a purchase from Harry & David. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.497	HEB Grocery Buyer Propensity	Brand Propensities	Food & Drugstore	Retail	Food & Beverage	Household	Modeled	14,19	29,81	This audience consists of households in the top 15-20% of a model predicting a purchase from HEB Grocery. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.250	Hint Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	14,92	31,33	This audience consists of households in the top 15-20% of a model predicting a purchase from Hint. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.323	Home Chef	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	14,18	29,78	This audience consists of households in the top 15-20% of a model predicting a purchase from Home Chef. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.501	Instacart Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	15,09	31,69	This audience consists of households in the top 15-20% of a model predicting a purchase from Instacart. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.502	King Arthur Flour Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	12,50	26,26	This audience consists of households in the top 15-20% of a model predicting a purchase from King Arthur Flour. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.503	KL Wine Merchants Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	16,03	33,67	This audience consists of households in the top 15-20% of a model predicting a purchase from KL Wine Merchants. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.504	Kroger Buyer Propensity	Brand Propensities	Food & Drugstore	Retail	Food & Beverage	Household	Modeled	11,82	24,83	This audience consists of households in the top 15-20% of a model predicting a purchase from Kroger. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.505	Lindt & Sprungli Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	10,34	21,71	This audience consists of households in the top 15-20% of a model predicting a purchase from Lindt & Sprungli. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.330	Marley Spoon	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	14,58	30,61	This audience consists of households in the top 15-20% of a model predicting a purchase from Marley Spoon. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.507	naturebox.com Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	11,64	24,44	This audience consists of households in the top 15-20% of a model predicting a purchase from naturebox.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.508	Nespresso Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	15,24	32,01	This audience consists of households in the top 15-20% of a model predicting a purchase from Nespresso. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.509	Omaha Steaks Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	12,86	27,02	This audience consists of households in the top 15-20% of a model predicting a purchase from Omaha Steaks. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.480	Peapod Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	13,18	27,69	This audience consists of households in the top 15-20% of a model predicting a purchase from Peapod. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.510	Postmates Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	22,53	47,31	This audience consists of households in the top 15-20% of a model predicting a purchase from Postmates. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.524	Publix Buyer Propensity	Brand Propensities	Food & Drugstore	Retail	Food & Beverage	Household	Modeled	13,37	28,08	This audience consists of households in the top 15-20% of a model predicting a purchase from Publix. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.526	Ralphs Buyer Propensity	Brand Propensities	Food & Drugstore	Retail	Food & Beverage	Household	Modeled	14,92	31,32	This audience consists of households in the top 15-20% of a model predicting a purchase from Ralphs. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.511	Rite Aid Buyer Propensity	Brand Propensities	Food & Drugstore	Retail	Health & Beauty	Household	Modeled	14,11	29,63	This audience consists of households in the top 15-20% of a model predicting a purchase from Rite Aid. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.512	Safeway Buyer Propensity	Brand Propensities	Food & Drugstore	Retail	Food & Beverage	Household	Modeled	15,10	31,72	This audience consists of households in the top 15-20% of a model predicting a purchase from Safeway. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.515	Shipt Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	13,73	28,83	This audience consists of households in the top 15-20% of a model predicting a purchase from Shipt. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.531	Stop & Shop Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage	Retail	Household	Modeled	12,80	26,89	This audience consists of households in the top 15-20% of a model predicting a purchase from Stop & Shop. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.347	Sun Basket	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	16,38	34,40	This audience consists of households in the top 15-20% of a model predicting a purchase from Sun Basket. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.516	Swanson Vitamins Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage	Health & Beauty	Household	Modeled	12,35	25,93	This audience consists of households in the top 15-20% of a model predicting a purchase from Swanson Vitamins. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.517	The Vitamin Shoppe Buyer Propensity	Brand Propensities	Food & Drugstore	Retail	Health & Beauty	Household	Modeled	9,75	20,48	This audience consists of households in the top 15-20% of a model predicting a purchase from The Vitamin Shoppe. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.518	Thrive Market Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	6,69	14,06	This audience consists of households in the top 15-20% of a model predicting a purchase from Thrive Market. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.520	Vitamin World Buyer Propensity	Brand Propensities	Food & Drugstore	Retail	Health & Beauty	Household	Modeled	11,84	24,86	This audience consists of households in the top 15-20% of a model predicting a purchase from Vitamin World. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.546	Vons Buyer Propensity	Brand Propensities	Food & Drugstore	Retail	Food & Beverage	Household	Modeled	15,23	31,98	This audience consists of households in the top 15-20% of a model predicting a purchase from Vons. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.481	Walgreens Buyer Propensity	Brand Propensities	Food & Drugstore	Retail	Health & Beauty	Household	Modeled	13,04	27,39	This audience consists of households in the top 15-20% of a model predicting a purchase from Walgreens. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.547	Wegmans Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage	Retail	Household	Modeled	13,69	28,75	This audience consists of households in the top 15-20% of a model predicting a purchase from Wegmans. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.521	Weight Watchers International Buyer Propensity	Brand Propensities	Food & Drugstore	Health & Beauty	Fitness	Household	Modeled	12,97	27,23	This audience consists of households in the top 15-20% of a model predicting a purchase from Weight Watchers International. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.522	Whole Foods Market Buyer Propensity	Brand Propensities	Food & Drugstore	Retail	Health & Beauty	Household	Modeled	15,10	31,72	This audience consists of households in the top 15-20% of a model predicting a purchase from Whole Foods Market. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.523	Wine.com Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage	Alcoholic Beverages	Household	Modeled	14,42	30,28	This audience consists of households in the top 15-20% of a model predicting a purchase from Wine.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.551	Winn-Dixie Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage	Retail	Household	Modeled	12,74	26,75	This audience consists of households in the top 15-20% of a model predicting a purchase from Winn-Dixie. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.573	Bristol Farms Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	15,15	31,82	This audience consists of households in the top 10-20% of a model predicting a purchase from Bristol Farms. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.587	Cub Foods Buyer Propensity	Brand Propensities	Food & Drugstore	Retail		Household	Modeled	11,52	24,18	This audience consists of households in the top 10-20% of a model predicting a purchase from Cub Foods. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.591	Dinnerly Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	13,10	27,51	This audience consists of households in the top 10-20% of a model predicting a purchase from Dinnerly. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.601	Fareway Stores Buyer Propensity	Brand Propensities	Food & Drugstore	Retail		Household	Modeled	11,64	24,45	This audience consists of households in the top 10-20% of a model predicting a purchase from Fareway Stores. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.602	Favor Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	14,05	29,51	This audience consists of households in the top 10-20% of a model predicting a purchase from Favor. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.605	Food City Buyer Propensity	Brand Propensities	Food & Drugstore	Retail		Household	Modeled	10,32	21,68	This audience consists of households in the top 10-20% of a model predicting a purchase from Food City. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.606	Food Dudes Delivery Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	12,08	25,36	This audience consists of households in the top 10-20% of a model predicting a purchase from Food Dudes Delivery. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.620	H-Mart Buyer Propensity	Brand Propensities	Food & Drugstore	Retail		Household	Modeled	14,86	31,20	This audience consists of households in the top 10-20% of a model predicting a purchase from H-Mart. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.622	Hudson News Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage	Retail	Household	Modeled	13,82	29,02	This audience consists of households in the top 10-20% of a model predicting a purchase from Hudson News. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.623	Huel Buyer Propensity	Brand Propensities	Food & Drugstore	Health & Beauty		Household	Modeled	16,04	33,68	This audience consists of households in the top 10-20% of a model predicting a purchase from Huel. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.625	Ingles Markets Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	10,96	23,02	This audience consists of households in the top 10-20% of a model predicting a purchase from Ingles Markets. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.636	Lowes Foods Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	12,85	26,98	This audience consists of households in the top 10-20% of a model predicting a purchase from Lowes Foods. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.640	Mariano's Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	14,59	30,65	This audience consists of households in the top 10-20% of a model predicting a purchase from Mariano'S. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.641	Market Basket Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	13,24	27,80	This audience consists of households in the top 10-20% of a model predicting a purchase from Market Basket. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.642	Market Street Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	13,55	28,45	This audience consists of households in the top 10-20% of a model predicting a purchase from Market Street. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.645	Mealpal Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	14,33	30,09	This audience consists of households in the top 10-20% of a model predicting a purchase from Mealpal. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.646	Metro Market Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	12,67	26,60	This audience consists of households in the top 10-20% of a model predicting a purchase from Metro Market. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.651	Natural Grocers Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	13,25	27,83	This audience consists of households in the top 10-20% of a model predicting a purchase from Natural Grocers. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.658	Pavilions Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	15,09	31,69	This audience consists of households in the top 10-20% of a model predicting a purchase from Pavilions. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.671	QFC Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	13,80	28,98	This audience consists of households in the top 10-20% of a model predicting a purchase from Qfc. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.673	Randalls Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	14,74	30,95	This audience consists of households in the top 10-20% of a model predicting a purchase from Randalls. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.674	Restaurant Depot Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	16,97	35,64	This audience consists of households in the top 10-20% of a model predicting a purchase from Restaurant Depot. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.685	Susiecakes Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	14,26	29,94	This audience consists of households in the top 10-20% of a model predicting a purchase from Susiecakes. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.695	Trader Joe's Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	15,38	32,29	This audience consists of households in the top 10-20% of a model predicting a purchase from Trader Joe'S. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.706	Yamibuy Buyer Propensity	Brand Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	14,64	30,75	This audience consists of households in the top 10-20% of a model predicting a purchase from Yamibuy. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.308	Express Scripts	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	12,29	25,80	This audience consists of households in the top 15-20% of a model predicting a purchase from Express Scripts. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.525	1-800-Contacts Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	17,16	36,03	This audience consists of households in the top 15-20% of a model predicting a purchase from 1-800-Contacts. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.069	24 Hour Fitness Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	13,78	28,93	This audience consists of households in the top 15-20% of a model predicting a purchase from 24 Hour Fitness. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.077	Amwell Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	15,24	32,00	This audience consists of households in the top 15-20% of a model predicting a purchase from Amwell. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.260	Anastasia Beverly Hills Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	14,15	29,71	This audience consists of households in the top 15-20% of a model predicting a purchase from Anastasia Beverly Hills. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.292	Anytime Fitness	Brand Propensities	Health & Beauty	Fitness		Household	Modeled	12,74	26,75	This audience consists of households in the top 15-20% of a model predicting a purchase from Anytime Fitness. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.529	AVON Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	9,64	20,25	This audience consists of households in the top 15-20% of a model predicting a purchase from AVON. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.530	Bare Escentuals Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	12,96	27,21	This audience consists of households in the top 15-20% of a model predicting a purchase from Bare Escentuals. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.531	Bareminerals Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	11,41	23,95	This audience consists of households in the top 15-20% of a model predicting a purchase from Bareminerals. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.532	Beachbody Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	11,47	24,08	This audience consists of households in the top 15-20% of a model predicting a purchase from Beachbody. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.279	Beauty Bar Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	17,25	36,23	This audience consists of households in the top 15-20% of a model predicting a purchase from Beauty Bar. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.189	BetterHelp Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	15,50	32,55	This audience consists of households in the top 15-20% of a model predicting a purchase from BetterHelp. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.536	Birchbox Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	13,37	28,08	This audience consists of households in the top 15-20% of a model predicting a purchase from Birchbox. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.537	Bodybuilding.com Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty	Fitness	Household	Modeled	14,21	29,85	This audience consists of households in the top 15-20% of a model predicting a purchase from Bodybuilding.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.165	CityMD Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	12,95	27,20	This audience consists of households in the top 15-20% of a model predicting a purchase from CityMD. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.539	Clinique Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	12,63	26,52	This audience consists of households in the top 15-20% of a model predicting a purchase from Clinique. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.131	Crunch Fitness Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	14,92	31,34	This audience consists of households in the top 15-20% of a model predicting a purchase from Crunch Fitness. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.540	DermStore Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	13,55	28,46	This audience consists of households in the top 15-20% of a model predicting a purchase from DermStore. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.135	Doctor On Demand Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	13,88	29,15	This audience consists of households in the top 15-20% of a model predicting a purchase from Doctor On Demand. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.541	Dollar Shave Club Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	12,99	27,28	This audience consists of households in the top 15-20% of a model predicting a purchase from Dollar Shave Club. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.543	e.l.f. Cosmetics Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	7,41	15,56	This audience consists of households in the top 15-20% of a model predicting a purchase from e.l.f. Cosmetics. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.105	Equinox Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty	Fitness	Household	Modeled	15,76	33,11	This audience consists of households in the top 15-20% of a model predicting a purchase from Equinox. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.544	eSalon Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	13,18	27,68	This audience consists of households in the top 15-20% of a model predicting a purchase from eSalon. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.545	Estee Lauder Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	13,13	27,56	This audience consists of households in the top 15-20% of a model predicting a purchase from Estee Lauder. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.546	Fitbit Buyer Propensity	Brand Propensities	Health & Beauty	Fitness	Health & Beauty	Household	Modeled	13,24	27,81	This audience consists of households in the top 15-20% of a model predicting a purchase from Fitbit. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.311	Free People	Brand Propensities	Health & Beauty	Retail		Household	Modeled	16,96	35,61	This audience consists of households in the top 15-20% of a model predicting a purchase from Free People. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.090	Function of Beauty Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	14,56	30,58	This audience consists of households in the top 15-20% of a model predicting a purchase from Function of Beauty. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.548	Gillette Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	13,94	29,27	This audience consists of households in the top 15-20% of a model predicting a purchase from Gillette. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.316	Glasses USA	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	15,80	33,19	This audience consists of households in the top 15-20% of a model predicting a purchase from Glasses USA. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.315	Glasses.com	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	13,06	27,43	This audience consists of households in the top 15-20% of a model predicting a purchase from Glasses.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.091	Glossier Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	14,60	30,65	This audience consists of households in the top 15-20% of a model predicting a purchase from Glossier. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.324	Gold's Gym Buyer Propensity	Brand Propensities	Health & Beauty	Fitness	Health & Beauty	Household	Modeled	12,78	26,85	This audience consists of households in the top 15-20% of a model predicting a purchase from Gold's Gym. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.549	Harry's Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	13,99	29,39	This audience consists of households in the top 15-20% of a model predicting a purchase from Harry's. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.491	Headspace Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	14,90	31,30	This audience consists of households in the top 15-20% of a model predicting a purchase from Headspace. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.249	Heartland Dental Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	8,61	18,08	This audience consists of households in the top 15-20% of a model predicting a purchase from Heartland Dental. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.492	Herbalife Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty	Fitness	Household	Modeled	12,51	26,28	This audience consists of households in the top 15-20% of a model predicting a purchase from Herbalife. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.207	Ilia Beauty Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	15,26	32,05	This audience consists of households in the top 15-20% of a model predicting a purchase from Ilia Beauty. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.209	Inkbox Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	17,33	36,39	This audience consists of households in the top 15-20% of a model predicting a purchase from Inkbox. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.210	Ipsy Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	13,38	28,11	This audience consists of households in the top 15-20% of a model predicting a purchase from Ipsy. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.550	KIEHLS Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	15,11	31,72	This audience consists of households in the top 15-20% of a model predicting a purchase from KIEHLS. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.178	Kylie Cosmetics Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	14,23	29,89	This audience consists of households in the top 15-20% of a model predicting a purchase from Kylie Cosmetics. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.552	Lancome Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	14,16	29,74	This audience consists of households in the top 15-20% of a model predicting a purchase from Lancome. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.291	LensCrafters Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	13,15	27,61	This audience consists of households in the top 15-20% of a model predicting a purchase from LensCrafters. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.481	Lola Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	14,85	31,18	This audience consists of households in the top 15-20% of a model predicting a purchase from Lola. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.553	M.A.C Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	14,85	31,18	This audience consists of households in the top 15-20% of a model predicting a purchase from M.A.C. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.554	Madison-Reed Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	14,50	30,46	This audience consists of households in the top 15-20% of a model predicting a purchase from Madison-Reed. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.483	Manscaped Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	14,54	30,53	This audience consists of households in the top 15-20% of a model predicting a purchase from Manscaped. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.555	Mary Kay Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	11,74	24,65	This audience consists of households in the top 15-20% of a model predicting a purchase from Mary Kay. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.485	Massage Envy Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	16,06	33,73	This audience consists of households in the top 15-20% of a model predicting a purchase from Massage Envy. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.556	Maybelline Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	8,46	17,77	This audience consists of households in the top 15-20% of a model predicting a purchase from Maybelline. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.309	MedExpress Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	11,29	23,72	This audience consists of households in the top 15-20% of a model predicting a purchase from MedExpress. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.314	Mirror Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	14,70	30,87	This audience consists of households in the top 15-20% of a model predicting a purchase from Mirror. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.315	MyFitnessPal Buyer Propensity	Brand Propensities	Health & Beauty	Fitness	Health & Beauty	Household	Modeled	14,82	31,11	This audience consists of households in the top 15-20% of a model predicting a purchase from MyFitnessPal. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.488	Noom Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty	Fitness	Household	Modeled	13,50	28,36	This audience consists of households in the top 15-20% of a model predicting a purchase from Noom. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.151	Nutrafol Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	14,51	30,47	This audience consists of households in the top 15-20% of a model predicting a purchase from Nutrafol. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.489	Nutrisystem Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	13,22	27,77	This audience consists of households in the top 15-20% of a model predicting a purchase from Nutrisystem. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.084	Pearle Vision Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	12,65	26,57	This audience consists of households in the top 15-20% of a model predicting a purchase from Pearle Vision. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.085	Peloton Buyer Propensity	Brand Propensities	Health & Beauty	Fitness	Health & Beauty	Household	Modeled	18,38	38,59	This audience consists of households in the top 15-20% of a model predicting a purchase from Peloton. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.523	PillPack Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	12,18	25,58	This audience consists of households in the top 15-20% of a model predicting a purchase from PillPack. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.087	Planet Fitness Buyer Propensity	Brand Propensities	Health & Beauty	Fitness		Household	Modeled	12,20	25,61	This audience consists of households in the top 15-20% of a model predicting a purchase from Planet Fitness. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.562	Puritan's Pride Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	7,42	15,59	This audience consists of households in the top 15-20% of a model predicting a purchase from Puritan's Pride. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.563	Quest Diagnostics Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	13,58	28,52	This audience consists of households in the top 15-20% of a model predicting a purchase from Quest Diagnostics. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.125	Scentsy Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	10,83	22,74	This audience consists of households in the top 15-20% of a model predicting a purchase from Scentsy. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.565	Sephora Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	16,21	34,04	This audience consists of households in the top 15-20% of a model predicting a purchase from Sephora. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.566	SkinCareRx Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	14,18	29,78	This audience consists of households in the top 15-20% of a model predicting a purchase from SkinCareRx. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.126	Skinstore.com Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	13,53	28,41	This audience consists of households in the top 15-20% of a model predicting a purchase from Skinstore.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.530	SmileDirectClub Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty	Professional Services	Household	Modeled	20,68	43,42	This audience consists of households in the top 15-20% of a model predicting a purchase from SmileDirectClub. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.567	soul-cycle.com Buyer Propensity	Brand Propensities	Health & Beauty	Fitness	Health & Beauty	Household	Modeled	15,21	31,95	This audience consists of households in the top 15-20% of a model predicting a purchase from soul-cycle.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.533	Supercuts Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	15,19	31,91	This audience consists of households in the top 15-20% of a model predicting a purchase from Supercuts. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.568	The Body Shop Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	13,93	29,24	This audience consists of households in the top 15-20% of a model predicting a purchase from The Body Shop. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.569	The Honest Company Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	11,62	24,40	This audience consists of households in the top 15-20% of a model predicting a purchase from The Honest Company. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.570	ULTA Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	13,95	29,29	This audience consists of households in the top 15-20% of a model predicting a purchase from ULTA. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.241	Urban Decay Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	21,33	44,79	This audience consists of households in the top 15-20% of a model predicting a purchase from Urban Decay. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.230	Visionworks Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	13,11	27,52	This audience consists of households in the top 15-20% of a model predicting a purchase from Visionworks. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.254	YMCA Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty	Fitness	Household	Modeled	12,38	25,99	This audience consists of households in the top 15-20% of a model predicting a purchase from YMCA. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.255	YogaWorks Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty	Fitness	Household	Modeled	13,09	27,50	This audience consists of households in the top 15-20% of a model predicting a purchase from YogaWorks. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.571	Blink Fitness Buyer Propensity	Brand Propensities	Health & Beauty	Fitness		Household	Modeled	14,65	30,76	This audience consists of households in the top 10-20% of a model predicting a purchase from Blink Fitness. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.572	Booksy Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	13,72	28,82	This audience consists of households in the top 10-20% of a model predicting a purchase from Booksy. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.626	Isagenix Buyer Propensity	Brand Propensities	Health & Beauty	Food & Beverage		Household	Modeled	13,82	29,02	This audience consists of households in the top 10-20% of a model predicting a purchase from Isagenix. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.656	Pat Mcgrath Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	16,26	34,15	This audience consists of households in the top 10-20% of a model predicting a purchase from Pat Mcgrath. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.688	Talkspace Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	14,73	30,94	This audience consists of households in the top 10-20% of a model predicting a purchase from Talkspace. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.689	The Little Clinic Buyer Propensity	Brand Propensities	Health & Beauty	Health & Beauty		Household	Modeled	11,73	24,64	This audience consists of households in the top 10-20% of a model predicting a purchase from The Little Clinic. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.702	Waybetter Buyer Propensity	Brand Propensities	Health & Beauty	Tech		Household	Modeled	15,22	31,95	This audience consists of households in the top 10-20% of a model predicting a purchase from Waybetter. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.707	Youfit Buyer Propensity	Brand Propensities	Health & Beauty	Fitness		Household	Modeled	16,05	33,71	This audience consists of households in the top 10-20% of a model predicting a purchase from Youfit. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.720	Neutrogena Buyer Propensity	Brand Propensities	Health & Beauty	CPG	Health & Beauty	Household	Modeled	12,53	26,32	This audience consists of households in the top 10-20% of a model predicting a purchase from Neutrogena. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.291	Allergan	Brand Propensities	Health Supplements			Household	Modeled	13,51	28,37	This audience consists of households in the top 15-20% of a model predicting a purchase from Allergan. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.362	Pharmacies	Brand Propensities	Health Supplements	Health & Beauty		Household	Modeled	12,42	26,08	This audience consists of households in the top 15-20% of a model predicting a purchase from the Pharmacies category. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.670	310 Nutrition Buyer Propensity	Brand Propensities	Health Supplements	Food & Beverage		Household	Modeled	15,52	32,59	This audience consists of households in the top 10-20% of a model predicting a purchase from 310 Nutrition. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.607	Framebridge Buyer Propensity	Brand Propensities	Home	Retail		Household	Modeled	15,09	31,69	This audience consists of households in the top 10-20% of a model predicting a purchase from Framebridge. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.621	Home Reserve Buyer Propensity	Brand Propensities	Home	Home		Household	Modeled	15,80	33,17	This audience consists of households in the top 10-20% of a model predicting a purchase from Home Reserve. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.630	Keyme Buyer Propensity	Brand Propensities	Home	Home		Household	Modeled	14,26	29,94	This audience consists of households in the top 10-20% of a model predicting a purchase from Keyme. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.632	Landmark Home Warranty Buyer Propensity	Brand Propensities	Home	Home		Household	Modeled	12,57	26,39	This audience consists of households in the top 10-20% of a model predicting a purchase from Landmark Home Warranty. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.675	Rinse Buyer Propensity	Brand Propensities	Home	Professional Services		Household	Modeled	16,99	35,68	This audience consists of households in the top 10-20% of a model predicting a purchase from Rinse. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.725	Sherwin Williams Buyer Propensity	Brand Propensities	Home	Home	Retail	Household	Modeled	13,10	27,52	This audience consists of households in the top 10-20% of a model predicting a purchase from Sherwin Williams. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.359	Landscaping	Brand Propensities	Home & Garden	Professional Services		Household	Modeled	12,81	26,90	This audience consists of households in the top 15-20% of a model predicting a purchase from the Landscaping category. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.593	Ace Hardware Corporation Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	13,19	27,70	This audience consists of households in the top 15-20% of a model predicting a purchase from Ace Hardware Corporation. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.594	ADT Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	13,70	28,76	This audience consists of households in the top 15-20% of a model predicting a purchase from ADT. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.595	Angie's List Buyer Propensity	Brand Propensities	Home & Household Goods	Retail	Professional Services	Household	Modeled	13,55	28,45	This audience consists of households in the top 15-20% of a model predicting a purchase from Angie's List. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.078	Arhaus Buyer Propensity	Brand Propensities	Home & Household Goods	Retail	Home	Household	Modeled	14,40	30,23	This audience consists of households in the top 15-20% of a model predicting a purchase from Arhaus. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.079	Ashley Furniture Homestore Buyer Propensity	Brand Propensities	Home & Household Goods	Retail	Home	Household	Modeled	13,28	27,88	This audience consists of households in the top 15-20% of a model predicting a purchase from Ashley Furniture Homestore. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.596	Bath & Body Works Buyer Propensity	Brand Propensities	Home & Household Goods	Retail	Health & Beauty	Household	Modeled	12,71	26,68	This audience consists of households in the top 15-20% of a model predicting a purchase from Bath & Body Works. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.573	Bed Bath & Beyond Buyer Propensity	Brand Propensities	Home & Household Goods	Retail	Home	Household	Modeled	13,29	27,90	This audience consists of households in the top 15-20% of a model predicting a purchase from Bed Bath & Beyond. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.281	Blick Art Materials Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	14,73	30,93	This audience consists of households in the top 15-20% of a model predicting a purchase from Blick Art Materials. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.190	Blinds.com Buyer Propensity	Brand Propensities	Home & Household Goods	Retail	Home	Household	Modeled	13,48	28,32	This audience consists of households in the top 15-20% of a model predicting a purchase from Blinds.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.574	Bosch Buyer Propensity	Brand Propensities	Home & Household Goods	Home		Household	Modeled	12,04	25,28	This audience consists of households in the top 15-20% of a model predicting a purchase from Bosch. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.193	Brinks Home Security Buyer Propensity	Brand Propensities	Home & Household Goods	Home		Household	Modeled	13,29	27,90	This audience consists of households in the top 15-20% of a model predicting a purchase from Brinks Home Security. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.598	BrylaneHome Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	11,58	24,33	This audience consists of households in the top 15-20% of a model predicting a purchase from BrylaneHome. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.599	Build.com Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	14,41	30,27	This audience consists of households in the top 15-20% of a model predicting a purchase from Build.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.161	Casper Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	15,54	32,64	This audience consists of households in the top 15-20% of a model predicting a purchase from Casper. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.512	Christmas Tree Shops Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	12,97	27,25	This audience consists of households in the top 15-20% of a model predicting a purchase from Christmas Tree Shops. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.601	Crate & Barrel Buyer Propensity	Brand Propensities	Home & Household Goods	Retail	Home	Household	Modeled	14,43	30,30	This audience consists of households in the top 15-20% of a model predicting a purchase from Crate & Barrel. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.575	Cuisinart Buyer Propensity	Brand Propensities	Home & Household Goods	Home	Retail	Household	Modeled	13,42	28,19	This audience consists of households in the top 15-20% of a model predicting a purchase from Cuisinart. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.576	Dewalt Buyer Propensity	Brand Propensities	Home & Household Goods	Home	Retail	Household	Modeled	12,21	25,63	This audience consists of households in the top 15-20% of a model predicting a purchase from Dewalt. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.220	Frontpoint Buyer Propensity	Brand Propensities	Home & Household Goods	Home	Retail	Household	Modeled	12,86	27,00	This audience consists of households in the top 15-20% of a model predicting a purchase from Frontpoint. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.578	GE Buyer Propensity	Brand Propensities	Home & Household Goods	Home	Retail	Household	Modeled	15,40	32,35	This audience consists of households in the top 15-20% of a model predicting a purchase from GE. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.248	Harbor Freight Tools Buyer Propensity	Brand Propensities	Home & Household Goods	Home	Retail	Household	Modeled	12,43	26,11	This audience consists of households in the top 15-20% of a model predicting a purchase from Harbor Freight Tools. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.096	Hobby Lobby Buyer Propensity	Brand Propensities	Home & Household Goods	Retail	Home	Household	Modeled	12,27	25,76	This audience consists of households in the top 15-20% of a model predicting a purchase from Hobby Lobby. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.252	HomeGoods Buyer Propensity	Brand Propensities	Home & Household Goods	Retail	Home	Household	Modeled	14,55	30,55	This audience consists of households in the top 15-20% of a model predicting a purchase from HomeGoods. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.267	Houzz Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	13,32	27,96	This audience consists of households in the top 15-20% of a model predicting a purchase from Houzz. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.270	IKEA Buyer Propensity	Brand Propensities	Home & Household Goods	Retail	Home	Household	Modeled	15,12	31,76	This audience consists of households in the top 15-20% of a model predicting a purchase from IKEA. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.603	Joss & Main Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	8,90	18,70	This audience consists of households in the top 15-20% of a model predicting a purchase from Joss & Main. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.580	Keurig Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	12,80	26,88	This audience consists of households in the top 15-20% of a model predicting a purchase from Keurig. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.323	Kirkland's Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	12,86	27,00	This audience consists of households in the top 15-20% of a model predicting a purchase from Kirkland's. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.581	Kitchenaid Buyer Propensity	Brand Propensities	Home & Household Goods	Home		Household	Modeled	10,35	21,73	This audience consists of households in the top 15-20% of a model predicting a purchase from Kitchenaid. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.582	Kohler Buyer Propensity	Brand Propensities	Home & Household Goods	Home		Household	Modeled	12,65	26,56	This audience consists of households in the top 15-20% of a model predicting a purchase from Kohler. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.326	La-Z-Boy (LZB)	Brand Propensities	Home & Household Goods	Home		Household	Modeled	7,36	15,45	This audience consists of households in the top 15-20% of a model predicting a purchase from La-Z-Boy. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.583	Lowe's Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	13,73	28,82	This audience consists of households in the top 15-20% of a model predicting a purchase from Lowe's. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.308	Mattress Firm Buyer Propensity	Brand Propensities	Home & Household Goods	Home	Retail	Household	Modeled	15,19	31,89	This audience consists of households in the top 15-20% of a model predicting a purchase from Mattress Firm. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.605	Menard Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	11,26	23,64	This audience consists of households in the top 15-20% of a model predicting a purchase from Menard. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.184	Michaels Stores Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	13,77	28,92	This audience consists of households in the top 15-20% of a model predicting a purchase from Michaels Stores. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.585	Moen Buyer Propensity	Brand Propensities	Home & Household Goods	Home		Household	Modeled	12,46	26,17	This audience consists of households in the top 15-20% of a model predicting a purchase from Moen. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.521	Paper Source Buyer Propensity	Brand Propensities	Home & Household Goods	Retail	Home	Household	Modeled	17,14	35,99	This audience consists of households in the top 15-20% of a model predicting a purchase from Paper Source. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.086	Pier 1 Imports Buyer Propensity	Brand Propensities	Home & Household Goods	Retail	Home	Household	Modeled	15,38	32,29	This audience consists of households in the top 15-20% of a model predicting a purchase from Pier 1 Imports. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.586	Pottery Barn Buyer Propensity	Brand Propensities	Home & Household Goods	Retail	Home	Household	Modeled	13,58	28,52	This audience consists of households in the top 15-20% of a model predicting a purchase from Pottery Barn. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.607	Pottery Barn Kids Buyer Propensity	Brand Propensities	Home & Household Goods	Retail	Home	Household	Modeled	11,72	24,61	This audience consists of households in the top 15-20% of a model predicting a purchase from Pottery Barn Kids. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.197	Protection One Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	12,44	26,12	This audience consists of households in the top 15-20% of a model predicting a purchase from Protection One. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.198	Purple Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	14,51	30,46	This audience consists of households in the top 15-20% of a model predicting a purchase from Purple. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.202	Raymour & Flanigan Buyer Propensity	Brand Propensities	Home & Household Goods	Retail	Home	Household	Modeled	12,42	26,08	This audience consists of households in the top 15-20% of a model predicting a purchase from Raymour & Flanigan. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.527	Rent-A-Center Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	12,29	25,81	This audience consists of households in the top 15-20% of a model predicting a purchase from Rent-A-Center. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.609	Restoration Hardware Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	13,45	28,25	This audience consists of households in the top 15-20% of a model predicting a purchase from Restoration Hardware. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.205	Rooms To Go Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	12,44	26,13	This audience consists of households in the top 15-20% of a model predicting a purchase from Rooms To Go. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.340	Saatva	Brand Propensities	Home & Household Goods	Home		Household	Modeled	13,97	29,34	This audience consists of households in the top 15-20% of a model predicting a purchase from Saatva. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.587	Serta Buyer Propensity	Brand Propensities	Home & Household Goods	Home		Household	Modeled	16,28	34,19	This audience consists of households in the top 15-20% of a model predicting a purchase from Serta. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.140	Sleep Number Buyer Propensity	Brand Propensities	Home & Household Goods	Home		Household	Modeled	12,52	26,29	This audience consists of households in the top 15-20% of a model predicting a purchase from Sleep Number. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.142	Solar CIty Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	22,91	48,12	This audience consists of households in the top 15-20% of a model predicting a purchase from Solar City. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.109	Sur La Table Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	14,27	29,97	This audience consists of households in the top 15-20% of a model predicting a purchase from Sur La Table. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.112	The Container Store Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	14,69	30,85	This audience consists of households in the top 15-20% of a model predicting a purchase from The Container Store. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.113	The Home Depot Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	13,78	28,93	This audience consists of households in the top 15-20% of a model predicting a purchase from The Home Depot. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.116	Tractor Supply Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	11,95	25,09	This audience consists of households in the top 15-20% of a model predicting a purchase from Tractor Supply. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.118	True Value Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	12,16	25,54	This audience consists of households in the top 15-20% of a model predicting a purchase from True Value. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.543	TruGreen Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	12,81	26,90	This audience consists of households in the top 15-20% of a model predicting a purchase from TruGreen. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.224	Tuesday Morning Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	11,36	23,85	This audience consists of households in the top 15-20% of a model predicting a purchase from Tuesday Morning. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.544	U-haul Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	16,25	34,13	This audience consists of households in the top 15-20% of a model predicting a purchase from U-haul. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.242	Vistaprint Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	13,76	28,90	This audience consists of households in the top 15-20% of a model predicting a purchase from Vistaprint. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.589	Wayfair Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	13,55	28,46	This audience consists of households in the top 15-20% of a model predicting a purchase from Wayfair. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.590	West Elm Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	15,71	33,00	This audience consists of households in the top 15-20% of a model predicting a purchase from West Elm. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.591	Whirlpool Buyer Propensity	Brand Propensities	Home & Household Goods	Home		Household	Modeled	12,59	26,44	This audience consists of households in the top 15-20% of a model predicting a purchase from Whirlpool. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.610	Williams-Sonoma Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	13,31	27,95	This audience consists of households in the top 15-20% of a model predicting a purchase from Williams-Sonoma. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.253	World Market Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	15,12	31,76	This audience consists of households in the top 15-20% of a model predicting a purchase from World Market. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.592	Yankee Candle Buyer Propensity	Brand Propensities	Home & Household Goods	Home		Household	Modeled	8,54	17,93	This audience consists of households in the top 15-20% of a model predicting a purchase from Yankee Candle. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.258	Zoro Tools Buyer Propensity	Brand Propensities	Home & Household Goods	Home		Household	Modeled	12,22	25,65	This audience consists of households in the top 15-20% of a model predicting a purchase from Zoro Tools. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.593	Do It Best Buyer Propensity	Brand Propensities	Home & Household Goods	Retail		Household	Modeled	12,13	25,48	This audience consists of households in the top 10-20% of a model predicting a purchase from Do It Best. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.618	Helix Sleep Buyer Propensity	Brand Propensities	Home & Household Goods	Home	Retail	Household	Modeled	13,15	27,62	This audience consists of households in the top 10-20% of a model predicting a purchase from Helix Sleep. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.648	Mightynest Buyer Propensity	Brand Propensities	Home & Household Goods	Home		Household	Modeled	14,39	30,23	This audience consists of households in the top 10-20% of a model predicting a purchase from Mightynest. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.684	Sunrun Buyer Propensity	Brand Propensities	Home Renovation	Home		Household	Modeled	13,87	29,14	This audience consists of households in the top 10-20% of a model predicting a purchase from Sunrun. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.701	Waterworks Buyer Propensity	Brand Propensities	Home Renovation	Home		Household	Modeled	13,81	29,00	This audience consists of households in the top 10-20% of a model predicting a purchase from Waterworks. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.612	Allstate Insurance Buyer Propensity	Brand Propensities	Insurance	Financial Services		Household	Modeled	13,78	28,94	This audience consists of households in the top 15-20% of a model predicting a purchase from Allstate Insurance. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.103	Embrace Pet Insurance Buyer Propensity	Brand Propensities	Insurance	Financial Services		Household	Modeled	15,50	32,55	This audience consists of households in the top 15-20% of a model predicting a purchase from Embrace Pet Insurance. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.215	Farmers Insurance Buyer Propensity	Brand Propensities	Insurance	Financial Services		Household	Modeled	13,65	28,66	This audience consists of households in the top 15-20% of a model predicting a purchase from Farmers Insurance. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.221	Geico Buyer Propensity	Brand Propensities	Insurance	Financial Services		Household	Modeled	15,14	31,79	This audience consists of households in the top 15-20% of a model predicting a purchase from Geico. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.274	Kaiser Permanente Buyer Propensity	Brand Propensities	Insurance	Financial Services		Household	Modeled	15,47	32,49	This audience consists of households in the top 15-20% of a model predicting a purchase from Kaiser Permanente. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.290	Lemonade Buyer Propensity	Brand Propensities	Insurance	Financial Services		Household	Modeled	20,37	42,77	This audience consists of households in the top 15-20% of a model predicting a purchase from Lemonade. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.613	Progressive Casualty Insurance Company Buyer Propensity	Brand Propensities	Insurance	Financial Services		Household	Modeled	13,67	28,70	This audience consists of households in the top 15-20% of a model predicting a purchase from Progressive Casualty Insurance Company. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.170	Safeco Insurance Buyer Propensity	Brand Propensities	Insurance	Financial Services		Household	Modeled	13,09	27,49	This audience consists of households in the top 15-20% of a model predicting a purchase from Safeco Insurance. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.145	State Farm Insurance Buyer Propensity	Brand Propensities	Insurance	Financial Services		Household	Modeled	14,71	30,89	This audience consists of households in the top 15-20% of a model predicting a purchase from State Farm Insurance. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.117	Travelers Buyer Propensity	Brand Propensities	Insurance	Financial Services		Household	Modeled	13,95	29,29	This audience consists of households in the top 15-20% of a model predicting a purchase from Travelers. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.614	United Services Automobile Association Buyer Propensity	Brand Propensities	Insurance	Financial Services		Household	Modeled	16,05	33,70	This audience consists of households in the top 15-20% of a model predicting a purchase from United Services Automobile Association. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.603	Figo Pet Insurance Buyer Propensity	Brand Propensities	Insurance	Pet		Household	Modeled	15,04	31,58	This audience consists of households in the top 10-20% of a model predicting a purchase from Figo Pet Insurance. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.647	Metromile Buyer Propensity	Brand Propensities	Insurance	Auto		Household	Modeled	16,87	35,42	This audience consists of households in the top 10-20% of a model predicting a purchase from Metromile. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.557	Claire's Buyer Propensity	Brand Propensities	Jewelry	Retail		Household	Modeled	12,59	26,44	This audience consists of households in the top 15-20% of a model predicting a purchase from Claire's. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.496	Jared Buyer Propensity	Brand Propensities	Jewelry	Retail		Household	Modeled	12,98	27,26	This audience consists of households in the top 15-20% of a model predicting a purchase from Jared. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.497	Kay Jewelers Buyer Propensity	Brand Propensities	Jewelry	Retail		Household	Modeled	13,61	28,57	This audience consists of households in the top 15-20% of a model predicting a purchase from Kay Jewelers. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.553	Zales Buyer Propensity	Brand Propensities	Jewelry	Retail		Household	Modeled	11,24	23,60	This audience consists of households in the top 15-20% of a model predicting a purchase from Zales. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.669	Pura Vida Bracelets Buyer Propensity	Brand Propensities	Jewelry	Retail		Household	Modeled	11,87	24,94	This audience consists of households in the top 10-20% of a model predicting a purchase from Pura Vida Bracelets. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.676	Rocksbox Buyer Propensity	Brand Propensities	Jewelry	Retail		Household	Modeled	14,57	30,60	This audience consists of households in the top 10-20% of a model predicting a purchase from Rocksbox. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.678	Shinola Buyer Propensity	Brand Propensities	Jewelry	Retail		Household	Modeled	15,12	31,75	This audience consists of households in the top 10-20% of a model predicting a purchase from Shinola. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.691	Timex Buyer Propensity	Brand Propensities	Jewelry	Retail		Household	Modeled	12,39	26,02	This audience consists of households in the top 10-20% of a model predicting a purchase from Timex. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.074	AbcMouse Buyer Propensity	Brand Propensities	Kids Products	Education		Household	Modeled	12,24	25,70	This audience consists of households in the top 15-20% of a model predicting a purchase from AbcMouse. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.617	Aeropostale Buyer Propensity	Brand Propensities	Kids Products	Retail		Household	Modeled	11,97	25,13	This audience consists of households in the top 15-20% of a model predicting a purchase from Aeropostale. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.620	buybuy BABY Buyer Propensity	Brand Propensities	Kids Products	Retail		Household	Modeled	13,92	29,23	This audience consists of households in the top 15-20% of a model predicting a purchase from buybuy BABY. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.160	Care.com Buyer Propensity	Brand Propensities	Kids Products	Professional Services		Household	Modeled	14,02	29,44	This audience consists of households in the top 15-20% of a model predicting a purchase from Care.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.622	Diapers.com Buyer Propensity	Brand Propensities	Kids Products	Retail		Household	Modeled	10,83	22,75	This audience consists of households in the top 15-20% of a model predicting a purchase from Diapers.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.623	Disney Buyer Propensity	Brand Propensities	Kids Products	Retail		Household	Modeled	14,11	29,64	This audience consists of households in the top 15-20% of a model predicting a purchase from Disney. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.624	Fisher-Price Buyer Propensity	Brand Propensities	Kids Products	Home		Household	Modeled	6,24	13,11	This audience consists of households in the top 15-20% of a model predicting a purchase from Fisher-Price. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.219	Freshly Picked Buyer Propensity	Brand Propensities	Kids Products	Home		Household	Modeled	17,60	36,96	This audience consists of households in the top 15-20% of a model predicting a purchase from Freshly Picked. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.625	Gerber Buyer Propensity	Brand Propensities	Kids Products	Home		Household	Modeled	13,63	28,62	This audience consists of households in the top 15-20% of a model predicting a purchase from Gerber. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.247	Happiest Baby Buyer Propensity	Brand Propensities	Kids Products	Home		Household	Modeled	14,06	29,53	This audience consists of households in the top 15-20% of a model predicting a purchase from Happiest Baby. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.272	Janie and Jack Buyer Propensity	Brand Propensities	Kids Products	Home		Household	Modeled	13,84	29,05	This audience consists of households in the top 15-20% of a model predicting a purchase from Janie and Jack. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.276	Kidizen Buyer Propensity	Brand Propensities	Kids Products	Retail		Household	Modeled	14,68	30,83	This audience consists of households in the top 15-20% of a model predicting a purchase from Kidizen. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.628	LEGO Buyer Propensity	Brand Propensities	Kids Products	Retail		Household	Modeled	13,18	27,68	This audience consists of households in the top 15-20% of a model predicting a purchase from LEGO. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.293	Little Passport Buyer Propensity	Brand Propensities	Kids Products	Retail		Household	Modeled	11,99	25,17	This audience consists of households in the top 15-20% of a model predicting a purchase from Little Passport. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.631	Party City Buyer Propensity	Brand Propensities	Kids Products	Retail		Household	Modeled	14,10	29,62	This audience consists of households in the top 15-20% of a model predicting a purchase from Party City. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.139	Sittercity Buyer Propensity	Brand Propensities	Kids Products	Retail		Household	Modeled	14,03	29,46	This audience consists of households in the top 15-20% of a model predicting a purchase from Sittercity. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.632	The Children's Place Buyer Propensity	Brand Propensities	Kids Products	Retail		Household	Modeled	18,40	38,63	This audience consists of households in the top 15-20% of a model predicting a purchase from The Children's Place. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.114	The Little Gym Buyer Propensity	Brand Propensities	Kids Products	Retail		Household	Modeled	13,63	28,61	This audience consists of households in the top 15-20% of a model predicting a purchase from The Little Gym. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.633	Toys R Us Buyer Propensity	Brand Propensities	Kids Products	Retail		Household	Modeled	16,38	34,40	This audience consists of households in the top 15-20% of a model predicting a purchase from Toys R Us. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.233	Bergdorf Goodman Buyer Propensity	Brand Propensities	Luxury Brands	Retail		Household	Modeled	15,84	33,26	This audience consists of households in the top 15-20% of a model predicting a purchase from Bergdorf Goodman. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.297	Burberry Buyer Propensity	Brand Propensities	Luxury Brands	Retail		Household	Modeled	14,78	31,04	This audience consists of households in the top 15-20% of a model predicting a purchase from Burberry. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.304	Chanel Buyer Propensity	Brand Propensities	Luxury Brands	Retail		Household	Modeled	14,92	31,34	This audience consists of households in the top 15-20% of a model predicting a purchase from Chanel. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.244	Coach Buyer Propensity	Brand Propensities	Luxury Brands	Retail		Household	Modeled	14,69	30,85	This audience consists of households in the top 15-20% of a model predicting a purchase from Coach. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.321	Dior Buyer Propensity	Brand Propensities	Luxury Brands	Retail		Household	Modeled	15,33	32,20	This audience consists of households in the top 15-20% of a model predicting a purchase from Dior. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.092	Gucci Buyer Propensity	Brand Propensities	Luxury Brands	Retail		Household	Modeled	15,94	33,47	This audience consists of households in the top 15-20% of a model predicting a purchase from Gucci. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.095	Hermes Buyer Propensity	Brand Propensities	Luxury Brands	Retail		Household	Modeled	16,59	34,83	This audience consists of households in the top 15-20% of a model predicting a purchase from Hermes. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.180	Louis Vuitton Buyer Propensity	Brand Propensities	Luxury Brands	Retail		Household	Modeled	16,31	34,24	This audience consists of households in the top 15-20% of a model predicting a purchase from Louis Vuitton. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.306	Saks Fifth Avenue Buyer Propensity	Brand Propensities	Luxury Brands	Retail		Household	Modeled	15,53	32,61	This audience consists of households in the top 15-20% of a model predicting a purchase from Saks Fifth Avenue. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.322	Tiffany & Co. Buyer Propensity	Brand Propensities	Luxury Brands	Retail		Household	Modeled	19,43	40,79	This audience consists of households in the top 15-20% of a model predicting a purchase from Tiffany & Co. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.509	Cartier Buyer Propensity	Brand Propensities	Luxury Brands	Retail		Household	Modeled	17,91	37,62	This audience consists of households in the top 15-20% of a model predicting a purchase from Cartier. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.516	David Yurman Buyer Propensity	Brand Propensities	Luxury Brands	Retail		Household	Modeled	13,44	28,23	This audience consists of households in the top 15-20% of a model predicting a purchase from David Yurman. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.520	Omega Buyer Propensity	Brand Propensities	Luxury Brands	Retail		Household	Modeled	9,16	19,23	This audience consists of households in the top 15-20% of a model predicting a purchase from Omega. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.613	Giorgio Armani Buyer Propensity	Brand Propensities	Luxury Brands	Retail		Household	Modeled	15,45	32,45	This audience consists of households in the top 10-20% of a model predicting a purchase from Giorgio Armani. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.628	Jimmy Choo Buyer Propensity	Brand Propensities	Luxury Brands	Retail		Household	Modeled	14,19	29,79	This audience consists of households in the top 10-20% of a model predicting a purchase from Jimmy Choo. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.643	Matches Fashion Buyer Propensity	Brand Propensities	Luxury Brands	Retail		Household	Modeled	15,86	33,31	This audience consists of households in the top 10-20% of a model predicting a purchase from Matchesfashion. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.649	Mytheresa Buyer Propensity	Brand Propensities	Luxury Brands	Retail		Household	Modeled	15,27	32,06	This audience consists of households in the top 10-20% of a model predicting a purchase from Mytheresa. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.665	Prada Buyer Propensity	Brand Propensities	Luxury Brands	Retail		Household	Modeled	15,44	32,42	This audience consists of households in the top 10-20% of a model predicting a purchase from Prada. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.699	Versace Buyer Propensity	Brand Propensities	Luxury Brands	Retail		Household	Modeled	16,09	33,80	This audience consists of households in the top 10-20% of a model predicting a purchase from Versace. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.289	Alamo Drafthouse Cinema	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	14,89	31,28	This audience consists of households in the top 15-20% of a model predicting a purchase from Alamo Drafthouse Cinema. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.635	Ancestry.com Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment	Retail	Household	Modeled	13,33	28,00	This audience consists of households in the top 15-20% of a model predicting a purchase from Ancestry.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.186	Audiobooks Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	14,16	29,74	This audience consists of households in the top 15-20% of a model predicting a purchase from Audiobooks. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.636	Barnes & Noble Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment	Retail	Household	Modeled	13,40	28,13	This audience consists of households in the top 15-20% of a model predicting a purchase from Barnes & Noble. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.282	Blurb Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	14,03	29,47	This audience consists of households in the top 15-20% of a model predicting a purchase from Blurb. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.305	Chatbooks Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	13,50	28,35	This audience consists of households in the top 15-20% of a model predicting a purchase from Chatbooks. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.639	DraftKings Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	13,02	27,33	This audience consists of households in the top 15-20% of a model predicting a purchase from DraftKings. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.102	Duolingo Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	13,67	28,71	This audience consists of households in the top 15-20% of a model predicting a purchase from Duolingo. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.640	Eventbrite Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	15,37	32,27	This audience consists of households in the top 15-20% of a model predicting a purchase from Eventbrite. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.641	Fandango Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	14,27	29,97	This audience consists of households in the top 15-20% of a model predicting a purchase from Fandango. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.505	Financial Times Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	14,61	30,68	This audience consists of households in the top 15-20% of a model predicting a purchase from Financial Times. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.643	Gamestop Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	11,87	24,92	This audience consists of households in the top 15-20% of a model predicting a purchase from Gamestop. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.645	Google Play Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	15,74	33,06	This audience consists of households in the top 15-20% of a model predicting a purchase from Google Play. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.320	Guitar Center	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	13,89	29,16	This audience consists of households in the top 15-20% of a model predicting a purchase from Guitar Center. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.094	Half Price Books Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	12,61	26,48	This audience consists of households in the top 15-20% of a model predicting a purchase from Half Price Books. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.268	Hunt A Killer Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	14,04	29,49	This audience consists of households in the top 15-20% of a model predicting a purchase from Hunt A Killer. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.648	iTunes Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	9,40	19,74	This audience consists of households in the top 15-20% of a model predicting a purchase from iTunes. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.294	Linkedin Learning Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	12,34	25,91	This audience consists of households in the top 15-20% of a model predicting a purchase from Lynda. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.649	Live Nation Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	12,74	26,76	This audience consists of households in the top 15-20% of a model predicting a purchase from Live Nation. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.482	Los Angeles Times Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	16,59	34,85	This audience consists of households in the top 15-20% of a model predicting a purchase from Los Angeles Times. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.307	MasterClass Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	14,55	30,56	This audience consists of households in the top 15-20% of a model predicting a purchase from MasterClass. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.361	Music Streaming	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	14,19	29,80	This audience consists of households in the top 15-20% of a model predicting a purchase from the Music Streaming category. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.518	NY Times Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	13,66	28,69	This audience consists of households in the top 15-20% of a model predicting a purchase from Ny Times. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.082	OurTime Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	13,75	28,88	This audience consists of households in the top 15-20% of a model predicting a purchase from OurTime. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.653	Pandora Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	13,22	27,76	This audience consists of households in the top 15-20% of a model predicting a purchase from Pandora. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.522	People Magazine Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	12,80	26,89	This audience consists of households in the top 15-20% of a model predicting a purchase from People Magazine. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.335	Pic Monkey	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	13,24	27,81	This audience consists of households in the top 15-20% of a model predicting a purchase from Pic Monkey. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.654	pokerstars.net Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	9,47	19,90	This audience consists of households in the top 15-20% of a model predicting a purchase from pokerstars.net. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.200	Quizlet Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	19,45	40,85	This audience consists of households in the top 15-20% of a model predicting a purchase from Quizlet. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.656	Regal Cinemas Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	12,16	25,54	This audience consists of households in the top 15-20% of a model predicting a purchase from Regal Cinemas. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.339	Roblox	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	13,51	28,37	This audience consists of households in the top 15-20% of a model predicting a purchase from Roblox. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.167	Rosetta Stone Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	13,69	28,74	This audience consists of households in the top 15-20% of a model predicting a purchase from Rosetta Stone. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.173	Scholastic Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	12,45	26,15	This audience consists of households in the top 15-20% of a model predicting a purchase from Scholastic. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.341	SeatGeek	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	19,53	41,02	This audience consists of households in the top 15-20% of a model predicting a purchase from SeatGeek. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.658	Shutterfly Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	12,51	26,27	This audience consists of households in the top 15-20% of a model predicting a purchase from Shutterfly. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.659	SiriusXM Radio Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	12,82	26,92	This audience consists of households in the top 15-20% of a model predicting a purchase from SiriusXM Radio. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.660	Sony Network Entertainment International Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	27,07	56,85	This audience consists of households in the top 15-20% of a model predicting a purchase from Sony Network Entertainment International. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.661	Spotify Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	15,05	31,60	This audience consists of households in the top 15-20% of a model predicting a purchase from Spotify. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.662	Steam Community Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	18,03	37,85	This audience consists of households in the top 15-20% of a model predicting a purchase from Steam Community. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.663	StubHub Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	13,98	29,36	This audience consists of households in the top 15-20% of a model predicting a purchase from StubHub. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.534	The Economist Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	13,34	28,01	This audience consists of households in the top 15-20% of a model predicting a purchase from The Economist. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.537	The Wall Street Journal Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	9,50	19,95	This audience consists of households in the top 15-20% of a model predicting a purchase from The Wall Street Journal. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.538	The Washington Post Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	16,82	35,32	This audience consists of households in the top 15-20% of a model predicting a purchase from The Washington Post. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.665	Ticketfly Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	16,58	34,82	This audience consists of households in the top 15-20% of a model predicting a purchase from Ticketfly. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.666	Ticketmaster Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	13,31	27,95	This audience consists of households in the top 15-20% of a model predicting a purchase from Ticketmaster. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.669	wwe.com Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	14,73	30,93	This audience consists of households in the top 15-20% of a model predicting a purchase from wwe.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.567	AXS Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	12,15	25,51	This audience consists of households in the top 10-20% of a model predicting a purchase from Axs. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.659	Publishers Clearinghouse Buyer Propensity	Brand Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	17,68	37,13	This audience consists of households in the top 10-20% of a model predicting a purchase from Publishers Clearinghouse. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.711	Audible Buyer Propensity	Brand Propensities	Media & Entertainment	Tech	Media & Entertainment	Household	Modeled	14,95	31,39	This audience consists of households in the top 10-20% of a model predicting a purchase from Audible. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.635	Living Scriptures Buyer Propensity	Brand Propensities	Movies & Shows	Media & Entertainment		Household	Modeled	12,85	26,98	This audience consists of households in the top 10-20% of a model predicting a purchase from Living Scriptures. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.682	Splice Buyer Propensity	Brand Propensities	Movies & Shows	Media & Entertainment		Household	Modeled	15,98	33,55	This audience consists of households in the top 10-20% of a model predicting a purchase from Splice. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.708	Yousician Buyer Propensity	Brand Propensities	Music	Education		Household	Modeled	13,30	27,93	This audience consists of households in the top 10-20% of a model predicting a purchase from Yousician. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.318	Goodwill	Brand Propensities	Non-Profits	Non-Profit		Household	Modeled	13,65	28,66	This audience consists of households in the top 15-20% of a model predicting a purchase from Goodwill. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.356	World Vision	Brand Propensities	Non-Profits	Non-Profit		Household	Modeled	12,81	26,90	This audience consists of households in the top 15-20% of a model predicting a purchase from World Vision. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.714	Chevron Buyer Propensity	Brand Propensities	Oil & Gas	Oil & Gas		Household	Modeled	15,76	33,10	This audience consists of households in the top 10-20% of a model predicting a purchase from Chevron. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.717	Exxon Buyer Propensity	Brand Propensities	Oil & Gas	Oil & Gas		Household	Modeled	13,97	29,33	This audience consists of households in the top 10-20% of a model predicting a purchase from Exxon. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.722	Quik Trip Buyer Propensity	Brand Propensities	Oil & Gas	Oil & Gas		Household	Modeled	12,96	27,22	This audience consists of households in the top 10-20% of a model predicting a purchase from Quik Trip. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.724	Shell Buyer Propensity	Brand Propensities	Oil & Gas	Oil & Gas		Household	Modeled	14,51	30,48	This audience consists of households in the top 10-20% of a model predicting a purchase from Shell. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.727	Speedway Buyer Propensity	Brand Propensities	Oil & Gas	Oil & Gas		Household	Modeled	11,35	23,83	This audience consists of households in the top 10-20% of a model predicting a purchase from Speedway. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.729	Sunoco Buyer Propensity	Brand Propensities	Oil & Gas	Oil & Gas		Household	Modeled	15,37	32,27	This audience consists of households in the top 10-20% of a model predicting a purchase from Sunoco. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.731	Valero Buyer Propensity	Brand Propensities	Oil & Gas	Oil & Gas		Household	Modeled	13,99	29,37	This audience consists of households in the top 10-20% of a model predicting a purchase from Valero. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.313	Gander Mountain	Brand Propensities	Outerwear	Retail		Household	Modeled	10,79	22,67	This audience consists of households in the top 15-20% of a model predicting a purchase from Gander Mountain. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.577	Canada Goose Buyer Propensity	Brand Propensities	Outerwear	Retail		Household	Modeled	15,14	31,80	This audience consists of households in the top 10-20% of a model predicting a purchase from Canada Goose. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.624	Icebreaker Buyer Propensity	Brand Propensities	Outerwear	Retail		Household	Modeled	14,80	31,07	This audience consists of households in the top 10-20% of a model predicting a purchase from Icebreaker. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.614	Goby Buyer Propensity	Brand Propensities	Personal Care & Cosmetics	Health & Beauty		Household	Modeled	15,51	32,58	This audience consists of households in the top 10-20% of a model predicting a purchase from Goby. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.616	Great Clips Buyer Propensity	Brand Propensities	Personal Care & Cosmetics	Health & Beauty		Household	Modeled	11,62	24,41	This audience consists of households in the top 10-20% of a model predicting a purchase from Great Clips. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.617	Hair Cuttery Buyer Propensity	Brand Propensities	Personal Care & Cosmetics	Health & Beauty		Household	Modeled	12,96	27,21	This audience consists of households in the top 10-20% of a model predicting a purchase from Hair Cuttery. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.668	Prosper Buyer Propensity	Brand Propensities	Personal Finance	Financial Services		Household	Modeled	14,06	29,53	This audience consists of households in the top 10-20% of a model predicting a purchase from Prosper. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.671	Active & Tech-Savvy	Brand Propensities	Personas	Tech		Household	Modeled	13,32	27,97	This audience consists of households in the top 15-20% of a model predicting a purchase from Active & Tech-Savvy. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.672	Big Chain Shoppers	Brand Propensities	Personas	Retail		Household	Modeled	15,12	31,75	This audience consists of households in the top 15-20% of a model predicting a purchase from Big Chain Shoppers. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.673	Black Friday Buyer Propensity	Brand Propensities	Personas	Holiday	Retail	Household	Modeled	13,95	29,29	This audience consists of households in the top 15-20% of a model predicting a purchase from Black Friday. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.674	Connected Techies	Brand Propensities	Personas	Tech		Household	Modeled	11,16	23,44	This audience consists of households in the top 15-20% of a model predicting a purchase from Connected Techies. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.675	Cyber Monday Buyer Propensity	Brand Propensities	Personas	Holiday	Retail	Household	Modeled	15,54	32,64	This audience consists of households in the top 15-20% of a model predicting a purchase from Cyber Monday. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.676	Digital Checkout Buyers	Brand Propensities	Personas	Retail		Household	Modeled	10,78	22,63	This audience consists of households in the top 15-20% of a model predicting a purchase from Digital Checkout Buyers. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.677	DRTV Home Shoppers	Brand Propensities	Personas	Retail		Household	Modeled	12,35	25,93	This audience consists of households in the top 15-20% of a model predicting a purchase from DRTV Home Shoppers. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.678	Fashionistas	Brand Propensities	Personas	Health & Beauty	Retail	Household	Modeled	14,39	30,23	This audience consists of households in the top 15-20% of a model predicting a purchase from Fashionistas. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.679	Kitchen and Homebodies	Brand Propensities	Personas	Home		Household	Modeled	9,23	19,39	This audience consists of households in the top 15-20% of a model predicting a purchase from Kitchen and Homebodies. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.680	Suburban Home	Brand Propensities	Personas	Home		Household	Modeled	13,82	29,02	This audience consists of households in the top 15-20% of a model predicting a purchase from Suburban Home. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.681	Upscale Living	Brand Propensities	Personas	Home		Household	Modeled	14,66	30,79	This audience consists of households in the top 15-20% of a model predicting a purchase from Upscale Living. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.682	Urban Commuters	Brand Propensities	Personas	Home		Household	Modeled	10,76	22,59	This audience consists of households in the top 15-20% of a model predicting a purchase from Urban Commuters. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.684	1-800-PetMeds Buyer Propensity	Brand Propensities	Pets	Pet		Household	Modeled	13,63	28,61	This audience consists of households in the top 15-20% of a model predicting a purchase from 1-800-PetMeds. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.686	Chewy.com Buyer Propensity	Brand Propensities	Pets	Pet		Household	Modeled	14,27	29,96	This audience consists of households in the top 15-20% of a model predicting a purchase from Chewy.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.690	Petco Buyer Propensity	Brand Propensities	Pets	Pet		Household	Modeled	16,15	33,91	This audience consists of households in the top 15-20% of a model predicting a purchase from Petco. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.693	PetSmart Buyer Propensity	Brand Propensities	Pets	Pet		Household	Modeled	14,98	31,46	This audience consists of households in the top 15-20% of a model predicting a purchase from PetSmart. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.336	PrettyLitter	Brand Propensities	Pets	Pet		Household	Modeled	14,98	31,46	This audience consists of households in the top 15-20% of a model predicting a purchase from PrettyLitter. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
260.803	Purina Buyer Propensity	Brand Propensities	Pets	Pet		Household	Modeled	10,41	21,86	This audience consists of households in the top 15-20% of a model predicting a purchase from Purina. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.695	Royal Canin Buyer Propensity	Brand Propensities	Pets	Pet		Household	Modeled	15,08	31,66	This audience consists of households in the top 15-20% of a model predicting a purchase from Royal Canin. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.592	Dogtopia Buyer Propensity	Brand Propensities	Pets	Professional Services		Household	Modeled	15,40	32,34	This audience consists of households in the top 10-20% of a model predicting a purchase from Dogtopia. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.690	Time Magazine Buyer Propensity	Brand Propensities	Publications	Media & Entertainment		Household	Modeled	11,59	24,34	This audience consists of households in the top 10-20% of a model predicting a purchase from Time Magazine. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.555	Auntie Anne's Buyer Propensity	Brand Propensities	QSR	QSR		Household	Modeled	14,98	31,46	This audience consists of households in the top 15-20% of a model predicting a purchase from Auntie Anne's. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.477	Blue Bottle Buyer Propensity	Brand Propensities	QSR	QSR		Household	Modeled	21,45	45,05	This audience consists of households in the top 15-20% of a model predicting a purchase from Blue Bottle. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.556	Carl's Jr. Buyer Propensity	Brand Propensities	QSR	QSR		Household	Modeled	14,22	29,86	This audience consists of households in the top 15-20% of a model predicting a purchase from Carl's Jr. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.700	Chipotle Buyer Propensity	Brand Propensities	QSR	QSR	Food & Beverage	Household	Modeled	14,85	31,18	This audience consists of households in the top 15-20% of a model predicting a purchase from Chipotle. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.513	Cinnabon Buyer Propensity	Brand Propensities	QSR	QSR		Household	Modeled	14,85	31,19	This audience consists of households in the top 15-20% of a model predicting a purchase from Cinnabon. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.304	Del Taco	Brand Propensities	QSR	Food & Beverage		Household	Modeled	13,95	29,29	This audience consists of households in the top 15-20% of a model predicting a purchase from Del Taco. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.698	Domino's Buyer Propensity	Brand Propensities	QSR	QSR	Food & Beverage	Household	Modeled	13,34	28,02	This audience consists of households in the top 15-20% of a model predicting a purchase from Domino's. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.701	Dunkin Donuts Buyer Propensity	Brand Propensities	QSR	QSR	Food & Beverage	Household	Modeled	13,66	28,68	This audience consists of households in the top 15-20% of a model predicting a purchase from Dunkin Donuts. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.490	Golden Corral Buyer Propensity	Brand Propensities	QSR	QSR		Household	Modeled	11,87	24,93	This audience consists of households in the top 15-20% of a model predicting a purchase from Golden Corral. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.495	Jamba Juice Buyer Propensity	Brand Propensities	QSR	QSR		Household	Modeled	15,91	33,41	This audience consists of households in the top 15-20% of a model predicting a purchase from Jamba Juice. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.560	Jersey Mike's Subs Buyer Propensity	Brand Propensities	QSR	QSR		Household	Modeled	19,71	41,40	This audience consists of households in the top 15-20% of a model predicting a purchase from Jersey Mike's. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.498	KFC Buyer Propensity	Brand Propensities	QSR	QSR		Household	Modeled	12,54	26,33	This audience consists of households in the top 15-20% of a model predicting a purchase from Kentucky Fried Chicken. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.480	Krispy Kreme Buyer Propensity	Brand Propensities	QSR	QSR		Household	Modeled	24,36	51,15	This audience consists of households in the top 15-20% of a model predicting a purchase from Krispy Kreme. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.703	Panera Bread Buyer Propensity	Brand Propensities	QSR	QSR	Food & Beverage	Household	Modeled	14,19	29,81	This audience consists of households in the top 15-20% of a model predicting a purchase from Panera Bread. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.704	Papa John's Buyer Propensity	Brand Propensities	QSR	QSR	Food & Beverage	Household	Modeled	12,62	26,50	This audience consists of households in the top 15-20% of a model predicting a purchase from Papa John's. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.705	Pizza Hut Buyer Propensity	Brand Propensities	QSR	QSR	Food & Beverage	Household	Modeled	11,14	23,40	This audience consists of households in the top 15-20% of a model predicting a purchase from Pizza Hut. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.528	Sbarro Buyer Propensity	Brand Propensities	QSR	QSR		Household	Modeled	12,30	25,82	This audience consists of households in the top 15-20% of a model predicting a purchase from Sbarro. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.699	Starbucks Buyer Propensity	Brand Propensities	QSR	QSR	Food & Beverage	Household	Modeled	15,13	31,77	This audience consists of households in the top 15-20% of a model predicting a purchase from Starbucks. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.540	Tim Hortons Buyer Propensity	Brand Propensities	QSR	QSR		Household	Modeled	11,22	23,56	This audience consists of households in the top 15-20% of a model predicting a purchase from Tim Hortons. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.549	White Castle Buyer Propensity	Brand Propensities	QSR	QSR		Household	Modeled	12,80	26,88	This audience consists of households in the top 15-20% of a model predicting a purchase from White Castle. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.706	Wingstop Buyer Propensity	Brand Propensities	QSR	QSR	Food & Beverage	Household	Modeled	12,96	27,21	This audience consists of households in the top 15-20% of a model predicting a purchase from Wingstop. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.579	Carvel Buyer Propensity	Brand Propensities	QSR	Food & Beverage		Household	Modeled	14,19	29,79	This audience consists of households in the top 10-20% of a model predicting a purchase from Carvel. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.580	Chicken Express Buyer Propensity	Brand Propensities	QSR	Food & Beverage		Household	Modeled	11,45	24,04	This audience consists of households in the top 10-20% of a model predicting a purchase from Chicken Express. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.582	Church's Chicken Buyer Propensity	Brand Propensities	QSR	Food & Beverage		Household	Modeled	11,32	23,77	This audience consists of households in the top 10-20% of a model predicting a purchase from Church'S Chicken. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.583	Chuy's Buyer Propensity	Brand Propensities	QSR	Food & Beverage		Household	Modeled	11,88	24,94	This audience consists of households in the top 10-20% of a model predicting a purchase from Chuy'S. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.584	City Market Buyer Propensity	Brand Propensities	QSR	Food & Beverage		Household	Modeled	12,39	26,01	This audience consists of households in the top 10-20% of a model predicting a purchase from City Market. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.609	Fresh Brothers Buyer Propensity	Brand Propensities	QSR	Food & Beverage		Household	Modeled	14,72	30,92	This audience consists of households in the top 10-20% of a model predicting a purchase from Fresh Brothers. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.615	Golden Chick Buyer Propensity	Brand Propensities	QSR	Food & Beverage		Household	Modeled	11,46	24,07	This audience consists of households in the top 10-20% of a model predicting a purchase from Golden Chick. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.627	Jack In The Box Buyer Propensity	Brand Propensities	QSR	Food & Beverage		Household	Modeled	13,41	28,17	This audience consists of households in the top 10-20% of a model predicting a purchase from Jack In The Box. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.639	Marble Slab Creamery Buyer Propensity	Brand Propensities	QSR	Food & Beverage		Household	Modeled	12,68	26,63	This audience consists of households in the top 10-20% of a model predicting a purchase from Marble Slab Creamery. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.660	Peter Piper Pizza Buyer Propensity	Brand Propensities	QSR	Food & Beverage		Household	Modeled	13,32	27,98	This audience consists of households in the top 10-20% of a model predicting a purchase from Peter Piper Pizza. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.672	Rally's Buyer Propensity	Brand Propensities	QSR	Food & Beverage		Household	Modeled	10,79	22,65	This audience consists of households in the top 10-20% of a model predicting a purchase from Rally'S. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.677	Rusty Taco Buyer Propensity	Brand Propensities	QSR	Food & Beverage		Household	Modeled	13,64	28,64	This audience consists of households in the top 10-20% of a model predicting a purchase from Rusty Taco. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.686	Taco Bueno Buyer Propensity	Brand Propensities	QSR	Food & Beverage		Household	Modeled	12,26	25,74	This audience consists of households in the top 10-20% of a model predicting a purchase from Taco Bueno. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.687	Taco Cabana Buyer Propensity	Brand Propensities	QSR	Food & Beverage		Household	Modeled	13,12	27,56	This audience consists of households in the top 10-20% of a model predicting a purchase from Taco Cabana. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.709	Zaxby's Buyer Propensity	Brand Propensities	QSR	Food & Beverage		Household	Modeled	10,97	23,04	This audience consists of households in the top 10-20% of a model predicting a purchase from Zaxby'S. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.710	Arby's Buyer Propensity	Brand Propensities	QSR	Food & Beverage		Household	Modeled	11,56	24,28	This audience consists of households in the top 10-20% of a model predicting a purchase from Arby'S. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.713	Burger King Buyer Propensity	Brand Propensities	QSR	Food & Beverage		Household	Modeled	12,27	25,77	This audience consists of households in the top 10-20% of a model predicting a purchase from Burger King. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.715	Chick-Fil-A Buyer Propensity	Brand Propensities	QSR	Food & Beverage		Household	Modeled	13,15	27,62	This audience consists of households in the top 10-20% of a model predicting a purchase from Chick-Fil-A. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.716	Dairy Queen Buyer Propensity	Brand Propensities	QSR	Food & Beverage		Household	Modeled	11,25	23,62	This audience consists of households in the top 10-20% of a model predicting a purchase from Dairy Queen. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.718	Hardee's Buyer Propensity	Brand Propensities	QSR	Food & Beverage		Household	Modeled	10,27	21,56	This audience consists of households in the top 10-20% of a model predicting a purchase from Hardee'S. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.719	McDonald's Buyer Propensity	Brand Propensities	QSR	Food & Beverage		Household	Modeled	12,49	26,24	This audience consists of households in the top 10-20% of a model predicting a purchase from Mcdonald'S. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.723	Quiznos Buyer Propensity	Brand Propensities	QSR	Food & Beverage		Household	Modeled	12,18	25,57	This audience consists of households in the top 10-20% of a model predicting a purchase from Quiznos. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.726	Sonic Drive-In Buyer Propensity	Brand Propensities	QSR	Food & Beverage		Household	Modeled	10,49	22,02	This audience consists of households in the top 10-20% of a model predicting a purchase from Sonic Drive-In. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.728	Subway Buyer Propensity	Brand Propensities	QSR	Food & Beverage		Household	Modeled	10,99	23,07	This audience consists of households in the top 10-20% of a model predicting a purchase from Subway. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.730	Taco Bell Buyer Propensity	Brand Propensities	QSR	Food & Beverage		Household	Modeled	12,81	26,91	This audience consists of households in the top 10-20% of a model predicting a purchase from Taco Bell. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.732	Wendy's Buyer Propensity	Brand Propensities	QSR	Food & Beverage		Household	Modeled	13,35	28,03	This audience consists of households in the top 10-20% of a model predicting a purchase from Wendy'S. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.554	Applebee's Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	11,67	24,50	This audience consists of households in the top 15-20% of a model predicting a purchase from Applebee's. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.277	Bahama Breeze Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	14,86	31,21	This audience consists of households in the top 15-20% of a model predicting a purchase from Bahama Breeze. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.187	Baja Fresh Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	14,70	30,88	This audience consists of households in the top 15-20% of a model predicting a purchase from Baja Fresh. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.295	Blaze Pizza	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	15,42	32,38	This audience consists of households in the top 15-20% of a model predicting a purchase from Blaze Pizza. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.283	Bob Evans Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	11,04	23,18	This audience consists of households in the top 15-20% of a model predicting a purchase from Bob Evans. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.284	Bonefish Grill Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	13,89	29,17	This audience consists of households in the top 15-20% of a model predicting a purchase from Bonefish Grill. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.191	Boston Market Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	15,67	32,91	This audience consists of households in the top 15-20% of a model predicting a purchase from Boston Market. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.296	Buffalo Wild Wings Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	12,82	26,91	This audience consists of households in the top 15-20% of a model predicting a purchase from Buffalo Wild Wings. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.157	By CHLOE Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	19,16	40,24	This audience consists of households in the top 15-20% of a model predicting a purchase from By CHLOE. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.299	California Fish Grill Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	21,69	45,54	This audience consists of households in the top 15-20% of a model predicting a purchase from California Fish Grill. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.300	California Pizza Kitchen Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	14,53	30,50	This audience consists of households in the top 15-20% of a model predicting a purchase from California Pizza Kitchen. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.159	Capital Grille Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	13,21	27,75	This audience consists of households in the top 15-20% of a model predicting a purchase from Capital Grille. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.297	Checkers	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	13,77	28,92	This audience consists of households in the top 15-20% of a model predicting a purchase from Checkers. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.320	Cracker Barrel Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	12,08	25,37	This audience consists of households in the top 15-20% of a model predicting a purchase from Cracker Barrel. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.558	Denny's Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	12,94	27,17	This audience consists of households in the top 15-20% of a model predicting a purchase from Denny's. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.305	El Pollo Loco	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	14,92	31,33	This audience consists of households in the top 15-20% of a model predicting a purchase from El Pollo Loco. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.107	Ez Cater Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	13,91	29,21	This audience consists of households in the top 15-20% of a model predicting a purchase from Ez Cater. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.217	Five Guys Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	14,58	30,62	This audience consists of households in the top 15-20% of a model predicting a purchase from Five Guys. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.218	Fooda Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	15,07	31,65	This audience consists of households in the top 15-20% of a model predicting a purchase from Fooda. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.097	Hooters Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	15,21	31,94	This audience consists of households in the top 15-20% of a model predicting a purchase from Hooters. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.559	Houlihan's Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	18,82	39,52	This audience consists of households in the top 15-20% of a model predicting a purchase from Houlihan's. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.206	IHop Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	13,74	28,86	This audience consists of households in the top 15-20% of a model predicting a purchase from IHop. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.710	Longhorn Steakhouse Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	12,31	25,84	This audience consists of households in the top 15-20% of a model predicting a purchase from Longhorn Steakhouse. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.329	Marco's Pizza	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	12,40	26,03	This audience consists of households in the top 15-20% of a model predicting a purchase from Marco's Pizza. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.711	Noodles Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	12,62	26,51	This audience consists of households in the top 15-20% of a model predicting a purchase from Noodles. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.712	Olive Garden Buyer Propensity	Brand Propensities	Restaurants & Dining	QSR		Household	Modeled	12,61	26,48	This audience consists of households in the top 15-20% of a model predicting a purchase from Olive Garden. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.713	OpenTable Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	12,68	26,62	This audience consists of households in the top 15-20% of a model predicting a purchase from OpenTable. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.152	Outback Steakhouse Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	14,74	30,94	This audience consists of households in the top 15-20% of a model predicting a purchase from Outback Steakhouse. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.083	Panda Express Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	14,24	29,90	This audience consists of households in the top 15-20% of a model predicting a purchase from Panda Express. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.714	Papa Murphy's Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	11,63	24,43	This audience consists of households in the top 15-20% of a model predicting a purchase from Papa Murphy's. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.153	Pei Wei Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	14,48	30,40	This audience consists of households in the top 15-20% of a model predicting a purchase from Pei Wei. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.196	Potbelly Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	21,63	45,43	This audience consists of households in the top 15-20% of a model predicting a purchase from Potbelly. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.199	Qdoba Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	13,78	28,94	This audience consists of households in the top 15-20% of a model predicting a purchase from Qdoba. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.155	Red Lobster Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	13,47	28,28	This audience consists of households in the top 15-20% of a model predicting a purchase from Red Lobster. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.156	Red Robin Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	13,21	27,73	This audience consists of households in the top 15-20% of a model predicting a purchase from Red Robin. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.169	Round Table Pizza Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	13,72	28,81	This audience consists of households in the top 15-20% of a model predicting a purchase from Round Table Pizza. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.122	Ruby Tuesday Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	11,06	23,23	This audience consists of households in the top 15-20% of a model predicting a purchase from Ruby Tuesday. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.708	Seamless Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage	QSR	Household	Modeled	23,10	48,52	This audience consists of households in the top 15-20% of a model predicting a purchase from Seamless. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.176	Shake Shack Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	15,28	32,09	This audience consists of households in the top 15-20% of a model predicting a purchase from Shake Shack. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.141	Smashburger Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	15,08	31,66	This audience consists of households in the top 15-20% of a model predicting a purchase from Smashburger. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.110	Sweetgreen Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	16,82	35,32	This audience consists of households in the top 15-20% of a model predicting a purchase from Sweetgreen. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.129	Texas Roadhouse Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	11,89	24,97	This audience consists of households in the top 15-20% of a model predicting a purchase from Texas Roadhouse. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.234	TGI Fridays Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	14,33	30,09	This audience consists of households in the top 15-20% of a model predicting a purchase from TGI Fridays. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.235	Tijuana Flats Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	14,10	29,60	This audience consists of households in the top 15-20% of a model predicting a purchase from Tijuana Flats. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.240	Uno Pizzeria & Grill Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	18,34	38,50	This audience consists of households in the top 15-20% of a model predicting a purchase from Uno Pizzeria & Grill. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.353	Urban Plates	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	14,28	30,00	This audience consists of households in the top 15-20% of a model predicting a purchase from Urban Plates. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.262	Waffle House Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	11,49	24,14	This audience consists of households in the top 15-20% of a model predicting a purchase from Waffle House. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.231	Waitr Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	16,81	35,31	This audience consists of households in the top 15-20% of a model predicting a purchase from Waitr. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.355	Whataburger	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	11,47	24,09	This audience consists of households in the top 15-20% of a model predicting a purchase from Whataburger. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.265	Yard House Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	14,54	30,53	This audience consists of households in the top 15-20% of a model predicting a purchase from Yard House. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.574	Bubba's 33 Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	13,02	27,33	This audience consists of households in the top 10-20% of a model predicting a purchase from Bubba'S 33. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.581	Chowbus Buyer Propensity	Brand Propensities	Restaurants & Dining	Tech		Household	Modeled	15,17	31,86	This audience consists of households in the top 10-20% of a model predicting a purchase from Chowbus. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.585	Cookunity Buyer Propensity	Brand Propensities	Restaurants & Dining	Professional Services		Household	Modeled	16,83	35,35	This audience consists of households in the top 10-20% of a model predicting a purchase from Cookunity. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.600	Famous Toastery Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	13,70	28,78	This audience consists of households in the top 10-20% of a model predicting a purchase from Famous Toastery. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.611	Genghis Grill Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	13,90	29,19	This audience consists of households in the top 10-20% of a model predicting a purchase from Genghis Grill. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.629	Just Salad Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	15,29	32,11	This audience consists of households in the top 10-20% of a model predicting a purchase from Just Salad. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.631	La Madeleine Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	13,56	28,48	This audience consists of households in the top 10-20% of a model predicting a purchase from La Madeleine. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.634	Levain Bakery Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	14,92	31,34	This audience consists of households in the top 10-20% of a model predicting a purchase from Levain Bakery. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.654	Ocean Prime Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	14,78	31,05	This audience consists of households in the top 10-20% of a model predicting a purchase from Ocean Prime. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.655	Original Pancake House Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	13,21	27,75	This audience consists of households in the top 10-20% of a model predicting a purchase from Original Pancake House. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.661	Pinstripes Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	14,20	29,83	This audience consists of households in the top 10-20% of a model predicting a purchase from Pinstripes. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.662	Pluckers Wing Bar Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	13,28	27,88	This audience consists of households in the top 10-20% of a model predicting a purchase from Pluckers Wing Bar. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.666	Pret A Manger Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	15,00	31,51	This audience consists of households in the top 10-20% of a model predicting a purchase from Pret A Manger. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.694	Toast Buyer Propensity	Brand Propensities	Restaurants & Dining	Tech		Household	Modeled	15,42	32,38	This audience consists of households in the top 10-20% of a model predicting a purchase from Toast. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.696	Twin Peaks Buyer Propensity	Brand Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	12,91	27,10	This audience consists of households in the top 10-20% of a model predicting a purchase from Twin Peaks. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.717	Academy Sports Outdoors Buyer Propensity	Brand Propensities	Sporting Goods	Retail		Household	Modeled	11,06	23,22	This audience consists of households in the top 15-20% of a model predicting a purchase from Academy Sports Outdoors. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.718	active.com Buyer Propensity	Brand Propensities	Sporting Goods	Retail		Household	Modeled	14,33	30,10	This audience consists of households in the top 15-20% of a model predicting a purchase from active.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.719	Athleta Buyer Propensity	Brand Propensities	Sporting Goods	Retail		Household	Modeled	14,11	29,63	This audience consists of households in the top 15-20% of a model predicting a purchase from Athleta. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.720	Backcountry.com Buyer Propensity	Brand Propensities	Sporting Goods	Retail		Household	Modeled	13,94	29,28	This audience consists of households in the top 15-20% of a model predicting a purchase from Backcountry.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.721	Bass Pro Shops Buyer Propensity	Brand Propensities	Sporting Goods	Retail		Household	Modeled	11,15	23,42	This audience consists of households in the top 15-20% of a model predicting a purchase from Bass Pro Shops. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.722	Cabela's Buyer Propensity	Brand Propensities	Sporting Goods	Retail		Household	Modeled	10,65	22,36	This audience consists of households in the top 15-20% of a model predicting a purchase from Cabela's. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.723	DICK'S Buyer Propensity	Brand Propensities	Sporting Goods	Retail		Household	Modeled	12,55	26,36	This audience consists of households in the top 15-20% of a model predicting a purchase from DICK'S. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.726	Finish Line Buyer Propensity	Brand Propensities	Sporting Goods	Retail		Household	Modeled	13,00	27,30	This audience consists of households in the top 15-20% of a model predicting a purchase from Finish Line. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.317	Golf Galaxy	Brand Propensities	Sporting Goods	Sports		Household	Modeled	12,89	27,07	This audience consists of households in the top 15-20% of a model predicting a purchase from Golf Galaxy. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.487	Moosejaw Buyer Propensity	Brand Propensities	Sporting Goods	Retail		Household	Modeled	13,34	28,02	This audience consists of households in the top 15-20% of a model predicting a purchase from Moosejaw. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.728	REI Buyer Propensity	Brand Propensities	Sporting Goods	Retail		Household	Modeled	14,03	29,46	This audience consists of households in the top 15-20% of a model predicting a purchase from REI. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.354	West Marine	Brand Propensities	Sporting Goods	Retail		Household	Modeled	11,93	25,05	This audience consists of households in the top 15-20% of a model predicting a purchase from West Marine. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.576	Camping World Buyer Propensity	Brand Propensities	Sporting Goods	Retail	Sports	Household	Modeled	11,98	25,15	This audience consists of households in the top 10-20% of a model predicting a purchase from Camping World. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.680	Sidelineswap Buyer Propensity	Brand Propensities	Sporting Goods	Sports		Household	Modeled	12,71	26,69	This audience consists of households in the top 10-20% of a model predicting a purchase from Sidelineswap. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.068	1password Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	15,39	32,31	This audience consists of households in the top 15-20% of a model predicting a purchase from 1password. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.075	Afterpay Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	12,18	25,58	This audience consists of households in the top 15-20% of a model predicting a purchase from Afterpay. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.730	AT&T Subscriber Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	14,21	29,83	This audience consists of households in the top 15-20% of a model predicting a purchase from AT&T. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.478	Boingo Wireless Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	14,96	31,41	This audience consists of households in the top 15-20% of a model predicting a purchase from Boingo Wireless. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.737	Boost Mobile Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	12,72	26,71	This audience consists of households in the top 15-20% of a model predicting a purchase from Boost Mobile. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.158	Calendly Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	15,74	33,05	This audience consists of households in the top 15-20% of a model predicting a purchase from Calendly. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.741	Cricket Wireless Subscriber Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	10,93	22,95	This audience consists of households in the top 15-20% of a model predicting a purchase from Cricket Wireless. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.133	Discord Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	15,71	32,99	This audience consists of households in the top 15-20% of a model predicting a purchase from Discord. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.136	DocuSign Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	18,01	37,83	This audience consists of households in the top 15-20% of a model predicting a purchase from DocuSign. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.100	Dropbox Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	15,84	33,27	This audience consists of households in the top 15-20% of a model predicting a purchase from Dropbox. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.106	ExpressVPN Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	16,24	34,10	This audience consists of households in the top 15-20% of a model predicting a purchase from ExpressVPN. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.504	FedEx Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	15,82	33,22	This audience consists of households in the top 15-20% of a model predicting a purchase from FedEx. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.222	GitHub Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	15,13	31,77	This audience consists of households in the top 15-20% of a model predicting a purchase from GitHub. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.223	GoFundMe Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	14,53	30,52	This audience consists of households in the top 15-20% of a model predicting a purchase from GoFundMe. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.244	Grammarly Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	24,29	51,01	This audience consists of households in the top 15-20% of a model predicting a purchase from Grammarly. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.289	LegalZoom Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	12,96	27,22	This audience consists of households in the top 15-20% of a model predicting a purchase from LegalZoom. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.295	Mailchimp Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	15,55	32,66	This audience consists of households in the top 15-20% of a model predicting a purchase from Mailchimp. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.310	Medium Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	17,55	36,86	This audience consists of households in the top 15-20% of a model predicting a purchase from Medium. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.746	MetroPCS Subscriber Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	12,45	26,14	This audience consists of households in the top 15-20% of a model predicting a purchase from Metro PCS. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.313	Minted Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	14,39	30,21	This audience consists of households in the top 15-20% of a model predicting a purchase from Minted. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.747	National Grid Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	16,36	34,35	This audience consists of households in the top 15-20% of a model predicting a purchase from National Grid. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.748	Net10 Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	10,27	21,57	This audience consists of households in the top 15-20% of a model predicting a purchase from Net10. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.749	Page Plus Cellular Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	15,46	32,47	This audience consists of households in the top 15-20% of a model predicting a purchase from Page Plus Cellular. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.750	PureTalk USA Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	23,55	49,46	This audience consists of households in the top 15-20% of a model predicting a purchase from PureTalk USA. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.751	Rebtel Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	14,60	30,67	This audience consists of households in the top 15-20% of a model predicting a purchase from Rebtel. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.752	Republic Wireless Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	12,27	25,77	This audience consists of households in the top 15-20% of a model predicting a purchase from Republic Wireless. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.753	Rogers Wireless Subscriber Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	43,90	92,19	This audience consists of households in the top 15-20% of a model predicting a purchase from Rogers Wireless. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.754	SoCalGas Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	21,14	44,39	This audience consists of households in the top 15-20% of a model predicting a purchase from SoCalGas. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.733	Sprint Subscriber Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	13,95	29,29	This audience consists of households in the top 15-20% of a model predicting a purchase from Sprint. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.144	Squarespace Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	16,38	34,40	This audience consists of households in the top 15-20% of a model predicting a purchase from Squarespace. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.755	Straight Talk Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	9,88	20,75	This audience consists of households in the top 15-20% of a model predicting a purchase from Straight Talk. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.111	TaskRabbit Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	22,24	46,70	This audience consists of households in the top 15-20% of a model predicting a purchase from TaskRabbit. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.536	The UPS Store Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	15,29	32,11	This audience consists of households in the top 15-20% of a model predicting a purchase from The UPS Store. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.734	T-Mobile Subscriber Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	15,14	31,80	This audience consists of households in the top 15-20% of a model predicting a purchase from T-Mobile. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.757	TracFone Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	10,72	22,51	This audience consists of households in the top 15-20% of a model predicting a purchase from TracFone. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.758	U.S. Cellular Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	11,55	24,25	This audience consists of households in the top 15-20% of a model predicting a purchase from U.S. Cellular. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.545	U.S. Mobile Subscriber Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	13,35	28,04	This audience consists of households in the top 15-20% of a model predicting a purchase from U.S. Mobile. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.228	UrbanSitter Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	16,25	34,13	This audience consists of households in the top 15-20% of a model predicting a purchase from UrbanSitter. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.735	Verizon Subscriber Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	13,72	28,82	This audience consists of households in the top 15-20% of a model predicting a purchase from Verizon. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.759	Virgin Mobile Subscriber Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	38,07	79,94	This audience consists of households in the top 15-20% of a model predicting a purchase from Virgin Mobile. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.243	Vonage Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	12,31	25,85	This audience consists of households in the top 15-20% of a model predicting a purchase from Vonage. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.233	WordPress Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom	Home	Household	Modeled	14,94	31,37	This audience consists of households in the top 15-20% of a model predicting a purchase from WordPress. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.256	Zillow Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom	Home	Household	Modeled	14,83	31,14	This audience consists of households in the top 15-20% of a model predicting a purchase from Zillow. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.257	Zoom Video Communications Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	14,56	30,57	This audience consists of households in the top 15-20% of a model predicting a purchase from Zoom Video Communications. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.564	Assurance Wireless Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	12,71	26,69	This audience consists of households in the top 10-20% of a model predicting a purchase from Assurance Wireless. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.679	Shipstation Buyer Propensity	Brand Propensities	Telecom & Service Providers	Telecom		Household	Modeled	14,80	31,08	This audience consists of households in the top 10-20% of a model predicting a purchase from Shipstation. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.761	Agoda Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	19,95	41,89	This audience consists of households in the top 15-20% of a model predicting a purchase from Agoda. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.762	Airbnb Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	15,60	32,76	This audience consists of households in the top 15-20% of a model predicting a purchase from Airbnb. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.763	Alamo Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	14,26	29,95	This audience consists of households in the top 15-20% of a model predicting a purchase from Alamo. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.764	Alaska Airlines Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	14,70	30,87	This audience consists of households in the top 15-20% of a model predicting a purchase from Alaska Airlines. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.765	American Airlines Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	14,91	31,32	This audience consists of households in the top 15-20% of a model predicting a purchase from American Airlines. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.766	Amtrak Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	14,53	30,52	This audience consists of households in the top 15-20% of a model predicting a purchase from Amtrak. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.767	Avis Car Rental Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	14,58	30,61	This audience consists of households in the top 15-20% of a model predicting a purchase from Avis Car Rental. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.768	Best Western Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	11,49	24,14	This audience consists of households in the top 15-20% of a model predicting a purchase from Best Western. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.769	Booking.com Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	8,65	18,17	This audience consists of households in the top 15-20% of a model predicting a purchase from Booking.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.479	Budget Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	12,32	25,88	This audience consists of households in the top 15-20% of a model predicting a purchase from Budget. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.195	Busch Gardens Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	14,54	30,53	This audience consists of households in the top 15-20% of a model predicting a purchase from Busch Gardens. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.771	Carnival Cruise Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	11,68	24,54	This audience consists of households in the top 15-20% of a model predicting a purchase from Carnival Cruise. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.162	Cedar Point Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	11,36	23,86	This audience consists of households in the top 15-20% of a model predicting a purchase from Cedar Point. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.773	Choice Hotels Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	12,09	25,38	This audience consists of households in the top 15-20% of a model predicting a purchase from Choice Hotels. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.514	Comfort Inn Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	11,09	23,28	This audience consists of households in the top 15-20% of a model predicting a purchase from Comfort Inn. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.299	Comfort Suites	Brand Propensities	Travel	Travel		Household	Modeled	11,32	23,77	This audience consists of households in the top 15-20% of a model predicting a purchase from Comfort Suites. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.301	Courtyard Inn	Brand Propensities	Travel	Travel		Household	Modeled	13,56	28,48	This audience consists of households in the top 15-20% of a model predicting a purchase from Courtyard Inn. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.515	Crowne Plaza Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	16,94	35,58	This audience consists of households in the top 15-20% of a model predicting a purchase from Crowne Plaza. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.303	Cubesmart	Brand Propensities	Travel	Professional Services		Household	Modeled	16,11	33,83	This audience consists of households in the top 15-20% of a model predicting a purchase from Cubesmart. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.517	Days Inn Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	11,42	23,99	This audience consists of households in the top 15-20% of a model predicting a purchase from Days Inn. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.774	Delta Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	15,26	32,05	This audience consists of households in the top 15-20% of a model predicting a purchase from Delta. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.134	Discovery Cove Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	13,37	28,08	This audience consists of households in the top 15-20% of a model predicting a purchase from Discovery Cove. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.779	Disney Cruise Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	18,09	37,98	This audience consists of households in the top 15-20% of a model predicting a purchase from Disney Cruise. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.499	Disney Resorts Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	13,37	28,07	This audience consists of households in the top 15-20% of a model predicting a purchase from Disney Resorts. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.775	Dollar Rent A Car Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	15,08	31,66	This audience consists of households in the top 15-20% of a model predicting a purchase from Dollar Rent A Car. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.099	Dorney Park Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	11,77	24,71	This audience consists of households in the top 15-20% of a model predicting a purchase from Dorney Park. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.500	Doubletree Hotel Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	13,27	27,87	This audience consists of households in the top 15-20% of a model predicting a purchase from Doubletree Hotel. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.501	Econo Lodge Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	10,64	22,35	This audience consists of households in the top 15-20% of a model predicting a purchase from Econo Lodge. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.502	Embassy Suites Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	12,74	26,75	This audience consists of households in the top 15-20% of a model predicting a purchase from Embassy Suites. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.776	Enterprise Rental Car Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	15,48	32,52	This audience consists of households in the top 15-20% of a model predicting a purchase from Enterprise Rental Car. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.777	Expedia Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	15,34	32,22	This audience consists of households in the top 15-20% of a model predicting a purchase from Expedia. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.503	Extended Stay America Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	16,54	34,73	This audience consists of households in the top 15-20% of a model predicting a purchase from Extended Stay America. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.309	Extra Space Storage	Brand Propensities	Travel	Professional Services		Household	Modeled	17,14	35,99	This audience consists of households in the top 15-20% of a model predicting a purchase from Extra Space Storage. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.778	Fairfield Inn Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	13,22	27,76	This audience consists of households in the top 15-20% of a model predicting a purchase from Fairfield Inn. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.507	Four Points Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	19,30	40,53	This audience consists of households in the top 15-20% of a model predicting a purchase from Four Points. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.780	Four Seasons Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	13,97	29,34	This audience consists of households in the top 15-20% of a model predicting a purchase from Four Seasons. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.781	Frontier Airlines Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	15,50	32,55	This audience consists of households in the top 15-20% of a model predicting a purchase from Frontier Airlines. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.245	Great America Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	11,04	23,19	This audience consists of households in the top 15-20% of a model predicting a purchase from Great America. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.321	Hampton Inn and Suites	Brand Propensities	Travel	Travel		Household	Modeled	12,65	26,56	This audience consists of households in the top 15-20% of a model predicting a purchase from Hampton Inn and Suites. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.784	Hertz Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	14,41	30,26	This audience consists of households in the top 15-20% of a model predicting a purchase from Hertz. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.785	Hilton Hotels & Resorts Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	13,19	27,70	This audience consists of households in the top 15-20% of a model predicting a purchase from Hilton Hotels & Resorts. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.493	Holiday Inn Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	8,45	17,74	This audience consists of households in the top 15-20% of a model predicting a purchase from Holiday Inn. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.251	Holland America Line Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	13,09	27,50	This audience consists of households in the top 15-20% of a model predicting a purchase from Holland America Line. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.786	HomeAway Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	13,83	29,04	This audience consists of households in the top 15-20% of a model predicting a purchase from HomeAway. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.787	Hotel Tonight Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	20,54	43,13	This audience consists of households in the top 15-20% of a model predicting a purchase from Hotel Tonight. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.788	Hotels.com Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	13,98	29,36	This audience consists of households in the top 15-20% of a model predicting a purchase from Hotels.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.494	Howard Johnson Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	15,23	31,99	This audience consists of households in the top 15-20% of a model predicting a purchase from Howard Johnson. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.790	Hyatt Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	14,11	29,63	This audience consists of households in the top 15-20% of a model predicting a purchase from Hyatt. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.324	Hyatt Place	Brand Propensities	Travel	Travel		Household	Modeled	14,28	30,00	This audience consists of households in the top 15-20% of a model predicting a purchase from Hyatt Place. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.791	IHG Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	12,85	26,99	This audience consists of households in the top 15-20% of a model predicting a purchase from IHG. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.792	JetBlue Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	15,11	31,74	This audience consists of households in the top 15-20% of a model predicting a purchase from JetBlue. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.793	kayak Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	18,78	39,44	This audience consists of households in the top 15-20% of a model predicting a purchase from kayak. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.287	Kings Island Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	14,30	30,03	This audience consists of households in the top 15-20% of a model predicting a purchase from Kings Island. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.288	Knotts Berry Farm Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	14,86	31,20	This audience consists of households in the top 15-20% of a model predicting a purchase from Knotts Berry Farm. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.325	La Quinta Motor Inns	Brand Propensities	Travel	Travel		Household	Modeled	12,04	25,28	This audience consists of households in the top 15-20% of a model predicting a purchase from La Quinta Motor Inns. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.794	Lyft Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	16,36	34,35	This audience consists of households in the top 15-20% of a model predicting a purchase from Lyft. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.328	Mandalay Bay	Brand Propensities	Travel	Travel		Household	Modeled	20,07	42,14	This audience consists of households in the top 15-20% of a model predicting a purchase from Mandalay Bay. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.795	Marriott Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	15,00	31,50	This audience consists of households in the top 15-20% of a model predicting a purchase from Marriott. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.796	MGM Grand Hotel & Casino Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	20,54	43,14	This audience consists of households in the top 15-20% of a model predicting a purchase from MGM Grand Hotel & Casino. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.797	MGM Resorts International Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	15,88	33,34	This audience consists of households in the top 15-20% of a model predicting a purchase from MGM Resorts International. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.798	National Car Rental Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	13,94	29,27	This audience consists of households in the top 15-20% of a model predicting a purchase from National Car Rental. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.799	Norwegian Cruise Line Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	14,06	29,53	This audience consists of households in the top 15-20% of a model predicting a purchase from Norwegian Cruise Line. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.800	Orbitz Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	15,12	31,75	This audience consists of households in the top 15-20% of a model predicting a purchase from Orbitz. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.801	Payless Car Rental Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	14,43	30,30	This audience consists of households in the top 15-20% of a model predicting a purchase from Payless Car Rental. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.802	Priceline Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	14,41	30,25	This audience consists of households in the top 15-20% of a model predicting a purchase from Priceline. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.337	Public Storage	Brand Propensities	Travel	Professional Services		Household	Modeled	15,95	33,49	This audience consists of households in the top 15-20% of a model predicting a purchase from Public Storage. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.525	Quality Inn Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	10,95	22,99	This audience consists of households in the top 15-20% of a model predicting a purchase from Quality Inn. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.203	Regent Seven Seas Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	12,67	26,60	This audience consists of households in the top 15-20% of a model predicting a purchase from Regent Seven Seas. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.338	Renaissance Hotels	Brand Propensities	Travel	Travel		Household	Modeled	13,62	28,60	This audience consists of households in the top 15-20% of a model predicting a purchase from Renaissance Hotels. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.804	Residence Inn Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	13,69	28,75	This audience consists of households in the top 15-20% of a model predicting a purchase from Residence Inn. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.805	Royal Caribbean Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	13,73	28,82	This audience consists of households in the top 15-20% of a model predicting a purchase from Royal Caribbean. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.171	San Diego zoo Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	14,34	30,12	This audience consists of households in the top 15-20% of a model predicting a purchase from San Diego zoo. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.806	Sandals Resorts Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	14,65	30,76	This audience consists of households in the top 15-20% of a model predicting a purchase from Sandals Resorts. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.174	Seabourn Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	13,82	29,02	This audience consists of households in the top 15-20% of a model predicting a purchase from Seabourn. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.807	SeaWorld Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	16,99	35,67	This audience consists of households in the top 15-20% of a model predicting a purchase from SeaWorld. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.175	Sesame Place Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	13,71	28,80	This audience consists of households in the top 15-20% of a model predicting a purchase from Sesame Place. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.529	Sheraton Hotel Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	13,76	28,89	This audience consists of households in the top 15-20% of a model predicting a purchase from Sheraton Hotel. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.808	Six Flags Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	13,92	29,24	This audience consists of households in the top 15-20% of a model predicting a purchase from Six Flags. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.810	Southwest Airlines Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	14,33	30,09	This audience consists of households in the top 15-20% of a model predicting a purchase from Southwest Airlines. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.811	Spirit Airlines Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	14,86	31,20	This audience consists of households in the top 15-20% of a model predicting a purchase from Spirit Airlines. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.344	Springhill Suites	Brand Propensities	Travel	Travel		Household	Modeled	12,59	26,43	This audience consists of households in the top 15-20% of a model predicting a purchase from Springhill Suites. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.532	Super 8 Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	11,58	24,31	This audience consists of households in the top 15-20% of a model predicting a purchase from Super 8. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.535	The Ritz Carlton Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	14,96	31,41	This audience consists of households in the top 15-20% of a model predicting a purchase from The Ritz Carlton. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.349	The Venetian Resort	Brand Propensities	Travel	Travel		Household	Modeled	14,38	30,19	This audience consists of households in the top 15-20% of a model predicting a purchase from The Venetian Resort. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.813	Thrifty Car Rental Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	14,03	29,46	This audience consists of households in the top 15-20% of a model predicting a purchase from Thrifty Car Rental. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.814	Travelocity Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	13,98	29,35	This audience consists of households in the top 15-20% of a model predicting a purchase from Travelocity. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.542	Travelodge Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	11,31	23,76	This audience consists of households in the top 15-20% of a model predicting a purchase from Travelodge. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.815	Travelzoo Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	14,42	30,29	This audience consists of households in the top 15-20% of a model predicting a purchase from Travelzoo. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.351	Tumi	Brand Propensities	Travel	Travel		Household	Modeled	15,27	32,06	This audience consists of households in the top 15-20% of a model predicting a purchase from Tumi. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.817	Uber Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	16,02	33,65	This audience consists of households in the top 15-20% of a model predicting a purchase from Uber. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.818	United Airlines Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	15,10	31,71	This audience consists of households in the top 15-20% of a model predicting a purchase from United Airlines. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.227	Universal Studios Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	15,09	31,69	This audience consists of households in the top 15-20% of a model predicting a purchase from Universal Studios. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.550	W Hotels Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	14,45	30,34	This audience consists of households in the top 15-20% of a model predicting a purchase from W Hotels. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.548	Westin Hotel Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	14,31	30,05	This audience consists of households in the top 15-20% of a model predicting a purchase from Westin Hotel. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.820	Wyndham Worldwide Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	12,61	26,47	This audience consists of households in the top 15-20% of a model predicting a purchase from Wyndham Worldwide. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.821	Yelp Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	15,96	33,51	This audience consists of households in the top 15-20% of a model predicting a purchase from Yelp. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.566	Away Buyer Propensity	Brand Propensities	Travel	Travel	Retail	Household	Modeled	15,33	32,19	This audience consists of households in the top 10-20% of a model predicting a purchase from Away. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.569	Baymont Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	10,99	23,09	This audience consists of households in the top 10-20% of a model predicting a purchase from Baymont. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.570	Bird Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	15,65	32,86	This audience consists of households in the top 10-20% of a model predicting a purchase from Bird. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.595	Egencia Buyer Propensity	Brand Propensities	Travel	Tech		Household	Modeled	13,88	29,16	This audience consists of households in the top 10-20% of a model predicting a purchase from Egencia. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.597	Europ Car Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	14,45	30,34	This audience consists of households in the top 10-20% of a model predicting a purchase from Europ Car. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.612	Gilroy Gardens Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	13,71	28,80	This audience consists of households in the top 10-20% of a model predicting a purchase from Gilroy Gardens. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.637	Mainstay Suites Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	10,77	22,62	This audience consists of households in the top 10-20% of a model predicting a purchase from Mainstay Suites. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.653	NYC Taxi Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	16,65	34,97	This audience consists of households in the top 10-20% of a model predicting a purchase from Nyc Taxi. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.681	Smartstop Self Storage Buyer Propensity	Brand Propensities	Travel	Professional Services		Household	Modeled	14,20	29,82	This audience consists of households in the top 10-20% of a model predicting a purchase from Smartstop Self Storage. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.683	Storquest Buyer Propensity	Brand Propensities	Travel	Professional Services		Household	Modeled	16,35	34,33	This audience consists of households in the top 10-20% of a model predicting a purchase from Storquest. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.698	Valleyfair Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	12,39	26,03	This audience consists of households in the top 10-20% of a model predicting a purchase from Valleyfair. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.700	Water Country Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	14,36	30,15	This audience consists of households in the top 10-20% of a model predicting a purchase from Water Country. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.703	Wingate Buyer Propensity	Brand Propensities	Travel	Travel		Household	Modeled	11,57	24,30	This audience consists of households in the top 10-20% of a model predicting a purchase from Wingate. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.704	Woodspring Suites Buyer Propensity	Brand Propensities	Travel	Tech		Household	Modeled	13,05	27,40	This audience consists of households in the top 10-20% of a model predicting a purchase from Woodspring Suites. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.823	Blizzard Buyer Propensity	Brand Propensities	Video Games	Media & Entertainment		Household	Modeled	13,36	28,05	This audience consists of households in the top 15-20% of a model predicting a purchase from Blizzard. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.824	Electronic Arts Buyer Propensity	Brand Propensities	Video Games	Media & Entertainment		Household	Modeled	14,36	30,16	This audience consists of households in the top 15-20% of a model predicting a purchase from Electronic Arts. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.104	Epic Games Store Buyer Propensity	Brand Propensities	Video Games	Media & Entertainment		Household	Modeled	16,74	35,16	This audience consists of households in the top 15-20% of a model predicting a purchase from Epic Games Store. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.825	GameFly Buyer Propensity	Brand Propensities	Video Games	Media & Entertainment		Household	Modeled	19,81	41,60	This audience consists of households in the top 15-20% of a model predicting a purchase from GameFly. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.088	PlayStation Network Buyer Propensity	Brand Propensities	Video Games	Media & Entertainment		Household	Modeled	13,56	28,48	This audience consists of households in the top 15-20% of a model predicting a purchase from PlayStation Network. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.204	Riot Games Buyer Propensity	Brand Propensities	Video Games	Media & Entertainment		Household	Modeled	15,63	32,83	This audience consists of households in the top 15-20% of a model predicting a purchase from Riot Games. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.225	Twitch Buyer Propensity	Brand Propensities	Video Games	Media & Entertainment		Household	Modeled	14,40	30,24	This audience consists of households in the top 15-20% of a model predicting a purchase from Twitch. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.259	Zynga Buyer Propensity	Brand Propensities	Video Games	Media & Entertainment		Household	Modeled	11,54	24,24	This audience consists of households in the top 15-20% of a model predicting a purchase from Zynga. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.652	Niantic Buyer Propensity	Brand Propensities	Video Games	Media & Entertainment		Household	Modeled	13,22	27,76	This audience consists of households in the top 10-20% of a model predicting a purchase from Niantic. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.721	Nintendo Buyer Propensity	Brand Propensities	Video Games	Media & Entertainment		Household	Modeled	14,25	29,93	This audience consists of households in the top 10-20% of a model predicting a purchase from Nintendo. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.830	Age 18-24	Demographics	Age	Demographics		Household	Known	9,04	18,97	Households that contain individuals aged 18-24. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses). For individuals in this age range use the Alliant Premium Age 18-24 segment.
12.833	Age 20-29	Demographics	Age	Demographics		Household	Known	17,38	36,50	Households that contain individuals aged 20-29. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses). For individuals in this age range use the Alliant Premium Age 20-29 segment.
12.831	Age 25-29	Demographics	Age	Demographics		Household	Known	11,70	24,57	Households that contain individuals aged 25-29. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses). For individuals in this age range use the Alliant Premium Age 25-29 segment.
12.834	Age 30-34	Demographics	Age	Demographics		Household	Known	16,32	34,28	Households that contain individuals aged 30-34. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses). For individuals in this age range use the Alliant Premium Age 30-34 segment.
12.836	Age 30-39	Demographics	Age	Demographics		Household	Known	29,87	62,72	Households that contain individuals aged 30-39. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses). For individuals in this age range use the Alliant Premium Age 30-39 segment.
12.835	Age 35-39	Demographics	Age	Demographics		Household	Known	17,40	36,54	Households that contain individuals aged 35-39. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses). For individuals in this age range use the Alliant Premium Age 35-39 segment.
12.837	Age 40-44	Demographics	Age	Demographics		Household	Known	17,84	37,46	Households that contain individuals aged 40-44. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses). For individuals in this age range use the Alliant Premium Age 40-44 segment.
12.839	Age 40-49	Demographics	Age	Demographics		Household	Known	30,33	63,68	Households that contain individuals aged 40-49. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses). For individuals in this age range use the Alliant Premium Age 40-49 segment.
12.838	Age 45-49	Demographics	Age	Demographics		Household	Known	16,27	34,16	Households that contain individuals aged 45-49. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses). For individuals in this age range use the Alliant Premium Age 45-49 segment.
12.841	Age 50-54	Demographics	Age	Demographics		Household	Known	16,53	34,71	Households that contain individuals aged 50-54. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses). For individuals in this age range use the Alliant Premium Age 50-54 segment.
12.843	Age 50-59	Demographics	Age	Demographics		Household	Known	29,68	62,32	Households that contain individuals aged 50-59. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses). For individuals in this age range use the Alliant Premium Age 50-59 segment.
12.842	Age 55-59	Demographics	Age	Demographics		Household	Known	16,96	35,61	Households that contain individuals aged 55-59. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses). For individuals in this age range use the Alliant Premium Age 55-59 segment.
12.846	Premium Age 18-24	Demographics	Age	Demographics		Individual	Known	5,98	12,56	Individuals aged 18-24. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.847	Premium Age 20-29	Demographics	Age	Demographics		Individual	Known	13,99	29,38	Individuals aged 20-29. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.848	Premium Age 25-29	Demographics	Age	Demographics		Individual	Known	8,64	18,14	Individuals aged 25-29. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.850	Premium Age 30-34	Demographics	Age	Demographics		Individual	Known	12,65	26,57	Individuals aged 30-34. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.852	Premium Age 30-39	Demographics	Age	Demographics		Individual	Known	26,86	56,41	Individuals aged 30-39. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.851	Premium Age 35-39	Demographics	Age	Demographics		Individual	Known	14,21	29,85	Individuals aged 35-39. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.853	Premium Age 40-44	Demographics	Age	Demographics		Individual	Known	14,90	31,28	Individuals aged 40-44. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.855	Premium Age 40-49	Demographics	Age	Demographics		Individual	Known	28,51	59,88	Individuals aged 40-49. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.854	Premium Age 45-49	Demographics	Age	Demographics		Individual	Known	13,62	28,60	Individuals aged 45-49. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.856	Premium Age 50-54	Demographics	Age	Demographics		Individual	Known	14,02	29,44	Individuals aged 50-54. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.858	Premium Age 50-59	Demographics	Age	Demographics		Individual	Known	28,52	59,90	Individuals aged 50-59. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.857	Premium Age 55-59	Demographics	Age	Demographics		Individual	Known	14,51	30,46	Individuals aged 55-59. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.865	Bachelors Degree	Demographics	Education	Demographics	Education	Household	Known	22,65	47,57	Households that contain individuals that have a Bachelors degree. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.864	College Graduates	Demographics	Education	Demographics	Education	Household	Modeled	24,77	52,02	Households that live in the top 10% of neighborhoods with college graduates. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.862	Did Not Graduate High School	Demographics	Education	Demographics	Education	Household	Known	9,65	20,27	Households that contain individuals that did not graduate high school. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.868	Educational Loan Propensity	Demographics	Education	Financial Services		Household	Modeled	12,40	26,03	This audience consists of households in the top 20% of a model predicting the likelihood that they have an educational loan. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
12.863	High School Graduate	Demographics	Education	Demographics	Education	Household	Known	21,65	45,46	Households that contain individuals that graduated high school. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.866	Post Graduate Degree	Demographics	Education	Demographics	Education	Household	Known	24,87	52,22	Households that contain individuals that have a post-Graduate degree. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.867	Premium College Graduates	Demographics	Education	Demographics	Education	Individual	Modeled	31,17	65,46	Individuals that live in the top 10% of neighborhoods with college graduates. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.881	Family Interests	Demographics	Family	Demographics	Home	Household	Inferred	15,44	32,43	Households that purchase children's products and family goods. Includes Children, Animals, Holiday, and Religious/Spiritual related products.
12.873	Female Head of Household	Demographics	Family	Demographics	Home	Household	Known	36,82	77,31	Households that contain a female head of household. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.880	Grandparent in Household	Demographics	Family	Demographics	Home	Household	Known	14,76	30,99	Households that contain a grandparent living in the home. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.870	Households with 1 Adult	Demographics	Family	Demographics	Home	Household	Known	45,24	95,01	Households that contain 1 adult. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.871	Households with 2 Adults	Demographics	Family	Demographics	Home	Household	Known	30,42	63,89	Households that contain 2 adults. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.872	Households with 3 Adults	Demographics	Family	Demographics	Home	Household	Known	29,40	61,74	Households that contain 3 adults. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.876	Husbands	Demographics	Family	Demographics	Home	Household	Known	35,32	74,18	Households that contain husbands. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.874	Male Head of Household	Demographics	Family	Demographics	Home	Household	Known	43,11	90,52	Households that contain a male head of household. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.878	Married	Demographics	Family	Demographics	Home	Household	Known	63,52	133,40	Households that contain spouses. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.890	Parents of Arts & Crafts Kids	Demographics	Family	Demographics	Home	Household	Known	798,25	1,68	Households that contain parents who purchase arts & crafts products. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.891	Parents of Babies/Newborns: Age 0-11 month	Demographics	Family	Demographics	Home	Household	Known	162,67	341,60	Households that contain a child who is 0-11 years old. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.892	Parents of Book Reading Kids	Demographics	Family	Demographics	Home	Household	Known	2,85	5,98	Households that contain parents who purchase books. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.895	Parents of Entertainment Kids	Demographics	Family	Demographics	Home	Household	Known	3,71	7,79	Households that contain parents who purchase entertainment products. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.897	Parents of Grade School Kids: Age 6-10	Demographics	Family	Demographics	Home	Household	Known	16,05	33,71	Households that contain a child who is 6-10 years old. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.902	Parents of Pre-School Kids: Age 3-5	Demographics	Family	Demographics	Home	Household	Known	6,80	14,28	Households that contain a child who is 3-5 years old. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.905	Parents of Sports Kids	Demographics	Family	Demographics	Home	Household	Known	1,93	4,04	Households that contain parents who purchase sports products. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.907	Parents of Teenagers: Age 14-17	Demographics	Family	Demographics	Home	Household	Known	16,42	34,48	Households that contain a child who is 14-17 years old. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.908	Parents of Toddlers: Age 1-2	Demographics	Family	Demographics	Home	Household	Known	2,92	6,13	Households that contain a child who is 1-2 years old. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.909	Parents of Tweens/Pre-teens: Age 11-13	Demographics	Family	Demographics	Home	Household	Known	8,45	17,74	Households that contain a child who is 11-13 years old. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.911	Premium Family Interests	Demographics	Family	Demographics	Home	Individual	Inferred	23,14	48,59	Individuals who purchase family-oriented products for children, pets, holidays, and religious matters.
12.916	Premium Family Married	Demographics	Family	Demographics	Home	Individual	Known	113,82	239,02	Individuals identified as spouses. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.917	Premium Family Single	Demographics	Family	Demographics	Home	Individual	Known	49,49	103,94	Individuals identified as single. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.912	Premium Female Head of Household	Demographics	Family	Demographics	Home	Individual	Known	33,02	69,35	Females that have been identified as the head of the household. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.914	Premium Husbands	Demographics	Family	Demographics	Home	Individual	Known	34,52	72,50	Individuals identified as husbands. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.913	Premium Male Head of Household	Demographics	Family	Demographics	Home	Individual	Known	41,61	87,38	Males that have been identified as the head of the household. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.921	Premium Parenting / Children	Demographics	Family	Demographics	Home	Individual	Known	8,42	17,68	Individuals who have purchased parenting related products, including books, magazines and videos offering advice on child rearing; topics include behavior & discipline, self-esteem, communication & bonding, and family activities for specific age groups.
12.920	Premium Spanish Spoken at Home	Demographics	Family	Demographics	Home	Individual	Inferred	20,14	42,30	Individuals that live in households with spanish speakers. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.915	Premium Wives	Demographics	Family	Demographics	Home	Individual	Known	32,16	67,54	Individuals identified as wives. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.883	Presence of Children Age 0-3	Demographics	Family	Demographics	Home	Household	Known	4,85	10,19	Households that contain a child who is 0-3 years old. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.886	Presence of Children Age 13-17	Demographics	Family	Demographics	Home	Household	Known	16,42	34,48	Households that contain a child who is 13-17 years old. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.884	Presence of Children Age 4-7	Demographics	Family	Demographics	Home	Household	Known	10,73	22,54	Households that contain a child who is 4-7 years old. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.885	Presence of Children Age 8-12	Demographics	Family	Demographics	Home	Household	Known	17,90	37,58	Households that contain a child who is 8-12 years old. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.879	Single	Demographics	Family	Demographics	Home	Household	Known	56,04	117,68	Households that contain an adult who is single. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.875	Spanish Spoken at Home	Demographics	Family	Demographics	Home	Household	Modeled	15,55	32,65	Households that contain a spanish speakers. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.877	Wives	Demographics	Family	Demographics	Home	Household	Known	34,17	71,75	Households that contain wives. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.923	Female	Demographics	Gender	Demographics		Household	Known	145,30	305,13	Household that contain an individual that self-identifies as female. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.924	Male	Demographics	Gender	Demographics		Household	Known	117,74	247,25	Household that contain an individual that self-identifies as male. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.926	Premium - Females	Demographics	Gender	Demographics		Individual	Known	145,30	305,13	Individuals that self-identify as female. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.927	Premium - Males	Demographics	Gender	Demographics		Individual	Known	117,74	247,25	Individuals that self-identify as male. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.929	Early Baby Boomers	Demographics	Generation	Demographics		Household	Known	22,93	48,15	Households that contain an adult born between 1946-1955. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses). For individuals in this age range use the Alliant Premium Early Baby Boomers segment.
12.931	Gen X	Demographics	Generation	Demographics		Household	Known	49,11	103,13	Households that contain an adult born between 1965-1983. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses). For individuals in this age range use the Alliant Premium Gen X segment.
12.932	Gen Y	Demographics	Generation	Demographics		Household	Known	39,41	82,76	Households that contain an adult born between 1984-2002. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses). For individuals in this age range use the Alliant Premium Gen Y segment.
12.930	Late Baby Boomers	Demographics	Generation	Demographics		Household	Known	26,48	55,61	Households that contain an adult born between 1956-1964. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses). For individuals in this age range use the Alliant Premium Late Baby Boomers segment.
12.933	Premium Early Baby Boomers	Demographics	Generation	Demographics		Individual	Known	22,00	46,20	Individuals born between 1946-1955. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.935	Premium Gen X	Demographics	Generation	Demographics		Individual	Known	48,55	101,95	Individuals born between 1965-1983. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.936	Premium Gen Y	Demographics	Generation	Demographics		Individual	Known	39,73	83,43	Individuals born between 1984-2002. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.934	Premium Late Baby Boomers	Demographics	Generation	Demographics		Individual	Known	24,93	52,36	Individuals born between 1956-1964. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.952	Household Income: $100k+	Demographics	Income	Demographics	Financial Services	Household	Known	51,04	107,18	Households that have an income of $100k or more. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.946	Household Income: $101,000-$110,000	Demographics	Income	Demographics	Financial Services	Household	Known	11,62	24,40	Households that have an income between $101,000 and $110,000. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.947	Household Income: $111,000-$120,000	Demographics	Income	Demographics	Financial Services	Household	Known	11,38	23,89	Households that have an income between $111,000 and $120,000. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.948	Household Income: $121,000-$130,000	Demographics	Income	Demographics	Financial Services	Household	Known	9,89	20,76	Households that have an income between $121,000 and $130,000. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.949	Household Income: $131,000-$140,000	Demographics	Income	Demographics	Financial Services	Household	Known	9,66	20,29	Households that have an income between $131,000 and $140,000. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.950	Household Income: $141,000-$150,000	Demographics	Income	Demographics	Financial Services	Household	Known	10,33	21,70	Households that have an income between $141,000 and $150,000. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.953	Household Income: $150k+	Demographics	Income	Demographics	Financial Services	Household	Known	25,39	53,33	Households that have an income of $150k or more. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.938	Household Income: $21,000-$30,000	Demographics	Income	Demographics	Financial Services	Household	Known	10,88	22,84	Households that have an income between $21,000 and $30,000. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.939	Household Income: $31,000-$40,000	Demographics	Income	Demographics	Financial Services	Household	Known	10,54	22,14	Households that have an income between $31,000 and $40,000. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.940	Household Income: $41,000-$50,000	Demographics	Income	Demographics	Financial Services	Household	Known	9,70	20,36	Households that have an income between $41,000 and $50,000. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.951	Household Income: $50k+	Demographics	Income	Demographics	Financial Services	Household	Known	77,59	162,94	Households that have an income of $50k or more. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.941	Household Income: $51,000-$60,000	Demographics	Income	Demographics	Financial Services	Household	Known	7,79	16,36	Households that have an income between $51,000 and $60,000. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.942	Household Income: $61,000-$70,000	Demographics	Income	Demographics	Financial Services	Household	Known	7,35	15,44	Households that have an income between $61,000 and $70,000. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.943	Household Income: $71,000-$80,000	Demographics	Income	Demographics	Financial Services	Household	Known	8,96	18,82	Households that have an income between $71,000 and $80,000. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.944	Household Income: $81,000-$90,000	Demographics	Income	Demographics	Financial Services	Household	Known	8,58	18,02	Households that have an income between $81,000 and $90,000. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.945	Household Income: $91,000-$100,000	Demographics	Income	Demographics	Financial Services	Household	Known	8,26	17,35	Households that have an income between $91,000 and $100,000. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.955	Premium Household Income: $100k+	Demographics	Income	Demographics	Financial Services	Individual	Known	92,34	193,90	Individuals in a household that has an income of $100k or more. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.956	Premium Household Income: $150k+	Demographics	Income	Demographics	Financial Services	Individual	Known	47,45	99,64	Individuals in a household that has an income of $150k or more. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.954	Premium Household Income: $50k+	Demographics	Income	Demographics	Financial Services	Individual	Known	141,34	296,81	Individuals in a household that has an income of $50k or more. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
161.829	New Births	Demographics	Life Stage	Demographics		Household	Known	535,75	1,13	Households that have birthed a child in the last 90 days. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
161.832	New Homeowners	Demographics	Life Stage	Demographics		Household	Inferred	810,33	1,70	Households that contain individuals who were previously renters and within the last 90 days have become homeowners. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
161.831	Newly Divorced	Demographics	Life Stage	Demographics		Individual	Known	592,33	1,24	Individuals that are newly divorced in the last 90 days. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
161.830	Newly Married	Demographics	Life Stage	Demographics		Individual	Known	1,04	2,18	Individuals that are newly married in the last 90 days. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.959	Boston	Demographics	Metro Area	Demographics		Household	Known	1,06	2,23	Households in the Boston Metro Area that are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the top 50% of buying activity in the Alliant cooperative.
12.960	Chicago	Demographics	Metro Area	Demographics		Household	Known	1,77	3,71	Households in the Chicago Metro Area that are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the top 50% of buying activity in the Alliant cooperative.
12.961	Dallas	Demographics	Metro Area	Demographics		Household	Known	1,41	2,95	Households in the Dallas Metro Area that are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the top 50% of buying activity in the Alliant cooperative.
12.963	Los Angeles	Demographics	Metro Area	Demographics		Household	Known	1,84	3,87	Households in the Los Angeles Metro Area that are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the top 50% of buying activity in the Alliant cooperative.
12.972	Metro Sports Fans - Boston	Demographics	Metro Area	Sports	Demographics	Household	Inferred	93,23	195,78	Households in the Boston Metro Area that are known sports product buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.971	Metro Sports Fans - Chicago	Demographics	Metro Area	Sports	Demographics	Household	Inferred	146,96	308,61	Households in the Chicago Metro Area that are known sports product buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.973	Metro Sports Fans - Dallas	Demographics	Metro Area	Sports	Demographics	Household	Inferred	106,86	224,41	Households in the Dallas Metro Area that are known sports product buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.969	Metro Sports Fans - New York	Demographics	Metro Area	Sports	Demographics	Household	Inferred	269,19	565,30	Households in the New York Metro Area that are known sports product buyers (via digital and offline channels from DTC businesses) in the Alliant cooperative.
12.964	Miami	Demographics	Metro Area	Demographics		Household	Known	1,02	2,14	Households in the Miami Metro Area that are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the top 50% of buying activity in the Alliant cooperative.
12.965	New York	Demographics	Metro Area	Demographics		Household	Known	3,49	7,33	Households in the New York Metro Area that are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the top 50% of buying activity in the Alliant cooperative.
12.966	Philadelphia	Demographics	Metro Area	Demographics		Household	Known	1,40	2,94	Households in the Philadelphia Metro Area that are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the top 50% of buying activity in the Alliant cooperative.
12.967	San Francisco	Demographics	Metro Area	Demographics		Household	Known	777,34	1,63	Households in the San Francisco Metro Area that are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the top 50% of buying activity in the Alliant cooperative.
12.968	Washington D.C.	Demographics	Metro Area	Demographics		Household	Known	1,35	2,83	Households in the Washington D.C. Metro Area that are also known multichannel buyers (via digital and offline channels from DTC businesses) who are scored with a payment performance model to identify those who are in the top 50% of buying activity in the Alliant cooperative.
12.975	Blue Collar Occupations	Demographics	Occupation	Demographics		Household	Modeled	15,43	32,39	Households that live in the top 10% of neighborhoods with blue collar workers. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.977	Management/Professional Occupations	Demographics	Occupation	Demographics		Household	Modeled	24,41	51,25	Households that live in the top 10% of neighborhoods with management or professional occupations. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.979	Premium Blue Collar Occupations	Demographics	Occupation	Demographics		Individual	Inferred	18,20	38,22	Individuals that live in households in the top 10% of neighborhoods with blue collar workers. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.980	Premium White Collar Occupations	Demographics	Occupation	Demographics		Individual	Inferred	28,80	60,49	Individuals that live in households in the top 10% of neighborhoods with white collar workers. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.982	Union Member Propensity	Demographics	Occupation	Demographics		Household	Modeled	11,50	24,16	This audience consists of households in the top 20% of a model predicting the likelihood that they have at least one member who belongs to a Union. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
12.976	White Collar Occupations	Demographics	Occupation	Demographics		Household	Modeled	22,74	47,75	Households that live in the top 10% of neighborhoods with white collar workers. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.978	Work at Home	Demographics	Occupation	Demographics	Home	Household	Inferred	88,41	185,65	Households that contain an individual that works from home. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.999	Premium Affluent Seniors	Demographics	Senior Market	Retail		Individual	Known	18,14	38,09	Individuals aged 60+ with a household income of $100,000 or more. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.004	Premium Charitable Seniors	Demographics	Senior Market	Non-Profit		Individual	Known	18,06	37,92	Individuals aged 60+ who have a propensity to donate to various types of charitable causes. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.990	Premium Health Conscious Seniors	Demographics	Senior Market	Health & Beauty	Fitness	Individual	Inferred	13,47	28,28	Individuals aged 60+ who have purchased health and wellness related products. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.989	Premium Senior Females	Demographics	Senior Market	Demographics		Individual	Known	33,50	70,35	Individuals aged 60+ who are female. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.995	Premium Senior Household Decision Makers	Demographics	Senior Market	Home		Individual	Inferred	41,24	86,60	Individuals aged 60+ in the Alliant database that purchase home products (via digital and offline channels from DTC businesses), meet their financial obligations and are in the top 50% payers in the Alliant cooperative. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.993	Premium Senior Internet Multibuyers	Demographics	Senior Market	Retail		Individual	Known	4,10	8,60	Individuals aged 60+ who have purchased multiple products via the internet. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.001	Premium Senior Investors	Demographics	Senior Market	Financial Services		Individual	Inferred	1,71	3,59	Individuals aged 60+ who purchased money or finance related products or have a propensity for online investment or trading. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.992	Premium Senior Multibuyers	Demographics	Senior Market	Retail		Individual	Known	14,13	29,68	Individuals aged 60+ who have purchased multiple products. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.003	Premium Senior Travelers	Demographics	Senior Market	Travel		Individual	Inferred	15,87	33,32	Individuals aged 60+ who purchase vacation/travel related products or have a propensity for cruise travel, foreign vacations, or taking frequent flights. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.991	Premium Seniors with a Mind for Fitness & Exercise	Demographics	Senior Market	Health & Beauty	Fitness	Individual	Inferred	5,46	11,46	Individuals aged 60+ who have purchased fitness and exercise related products. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.987	Estimated Wealth: $1,000,000+	Demographics	Wealth	Demographics	Financial Services	Household	Inferred	14,84	31,16	Households with an estimated wealth above $1,000,000. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.984	Estimated Wealth: $150,000-$300,000	Demographics	Wealth	Demographics	Financial Services	Household	Inferred	16,25	34,12	Households with an estimated wealth between $150,000 and $300,000. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.985	Estimated Wealth: $300,000-$550,000	Demographics	Wealth	Demographics	Financial Services	Household	Inferred	14,76	31,00	Households with an estimated wealth between $300,000 and $550,000. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
12.986	Estimated Wealth: $550,000-$1,000,000	Demographics	Wealth	Demographics	Financial Services	Household	Inferred	22,26	46,74	Households with an estimated wealth between $550,000 and $1,000,000. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.010	Premium Financially In Charge Young Professionals	Demographics	Young Professionals	Financial Services		Individual	Inferred	2,26	4,75	Individuals aged 20-39+ who have management/professional occupations, meet their financial obligations and are in the top 50% payers in the Alliant cooperative. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.008	Premium Young Female Professionals	Demographics	Young Professionals	Demographics		Individual	Known	2,25	4,72	Individuals aged 20-39+ who are female and have management/professional occupations. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.009	Premium Young Male Professionals	Demographics	Young Professionals	Demographics		Individual	Known	1,76	3,71	Individuals aged 20-39+ who are male and have management/professional occupations. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.007	Premium Young Professionals	Demographics	Young Professionals	Demographics		Individual	Known	4,19	8,80	Individuals aged 20-39+ who have management/professional occupations. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.015	Premium Young Professionals Interested in Fitness, Exercise & Health	Demographics	Young Professionals	Fitness	Health & Beauty	Individual	Inferred	317,33	666,40	Individuals aged 20-39+ who have management/professional occupations and have purchased health, fitness and exercise related products or services. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.011	Premium Young Professionals using Credit Cards	Demographics	Young Professionals	Financial Services		Individual	Known	1,78	3,73	Individuals aged 20-39+ who have management/professional occupations and paid for a purchase with a credit card. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.063	Adult Education - Propensity	Interest Propensities	Activities & Interests	Education		Household	Modeled	11,33	23,79	This audience consists of households in the top 20% of a model predicting they attend adult education classes at least twice a month. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.043	B2B Business Software	Interest Propensities	Activities & Interests	Tech		Household	Modeled	23,28	48,89	This audience consists of households in the top 15-20% of a model predicting an interest in B2B Business Software. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.044	B2B Career Advice	Interest Propensities	Activities & Interests	Professional Services		Household	Modeled	29,25	61,42	This audience consists of households in the top 15-20% of a model predicting an interest in B2B Career Advice. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.045	B2B Job Search	Interest Propensities	Activities & Interests	Professional Services		Household	Modeled	37,43	78,59	This audience consists of households in the top 15-20% of a model predicting an interest in B2B Job Search. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.046	Bicycling	Interest Propensities	Activities & Interests	Media & Entertainment		Household	Modeled	27,48	57,71	This audience consists of households in the top 15-20% of a model predicting an interest in bicycling. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.047	Buying and Selling Homes / Real Estate	Interest Propensities	Activities & Interests	Financial Services	Home	Household	Modeled	42,33	88,88	This audience consists of households in the top 15-20% of a model predicting an interest in buying and selling homes / real estate. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.048	Clothing	Interest Propensities	Activities & Interests	Retail		Household	Modeled	38,64	81,14	This audience consists of households in the top 15-20% of a model predicting an interest in clothing. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.049	College Life	Interest Propensities	Activities & Interests	Education		Household	Modeled	36,83	77,34	This audience consists of households in the top 15-20% of a model predicting an interest in college life. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.019	Comic Books	Interest Propensities	Activities & Interests	Media & Entertainment		Household	Modeled	52,51	110,27	This audience consists of households in the top 15-20% of a model predicting an interest in comic books. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.020	Dating	Interest Propensities	Activities & Interests	Media & Entertainment		Household	Modeled	38,06	79,92	This audience consists of households in the top 15-20% of a model predicting an interest in dating. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.021	Digital Payment Service Propensity	Interest Propensities	Activities & Interests	Professional Services		Household	Modeled	8,12	17,04	This audience consists of households in the top 20% of a model predicting the likelihood that they used a digital payment service (Apple Pay, Google Wallet, Master Pass, Pay Pal or Visa Checkout) in the last 30 days. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.023	Ecommerce	Interest Propensities	Activities & Interests	Retail		Household	Modeled	53,96	113,32	This audience consists of households in the top 15-20% of a model predicting an interest in ecommerce. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.022	Fantasy Sports Propensity	Interest Propensities	Activities & Interests	Media & Entertainment		Household	Modeled	8,74	18,36	This audience consists of households in the top 20% of a model predicting the likelihood that they engage in fantasy sports at least once per month. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.024	Fashion	Interest Propensities	Activities & Interests	Health & Beauty	Retail	Household	Modeled	34,71	72,89	This audience consists of households in the top 15-20% of a model predicting an interest in fashion. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.025	FIFA World Cup	Interest Propensities	Activities & Interests	Sports		Household	Modeled	15,75	33,07	This audience consists of households in the top 15-20% of a model predicting an interest in FIFA World Cup. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.026	Financial Aid	Interest Propensities	Activities & Interests	Financial Services		Household	Modeled	48,77	102,41	This audience consists of households in the top 15-20% of a model predicting an interest in financial aid. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.055	Golf Fans - Propensity	Interest Propensities	Activities & Interests	Media & Entertainment		Household	Modeled	12,08	25,37	This audience consists of households in the top 20% of a model predicting they attended golf tournaments in the past year. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.027	Guitar	Interest Propensities	Activities & Interests	Media & Entertainment		Household	Modeled	55,24	116,01	This audience consists of households in the top 15-20% of a model predicting an interest in guitar. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.054	High End Electronic Buyer - Propensity	Interest Propensities	Activities & Interests	Tech		Household	Modeled	11,93	25,05	This audience consists of households in the top 20% of a model predicting they own a combination of multiple electronics. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.029	High Value Stock Investor Propensity	Interest Propensities	Activities & Interests	Financial Services		Household	Modeled	11,39	23,91	This audience consists of households in the top 20% of a model predicting the likelihood that they have stocks with a total value of at least $100,000. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.028	High-End Sporting Equipment Propensity	Interest Propensities	Activities & Interests	Sports	Health & Beauty	Household	Modeled	9,11	19,13	This audience consists of households in the top 20% of a model predicting the likelihood that they have purchased high-end sporting equipment totaling over $250 in the last 12 months. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.067	Home Office - Propensity	Interest Propensities	Activities & Interests	Home		Household	Modeled	9,99	20,97	This audience consists of households in the top 20% of a model predicting they have a home office. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.056	Hunting - Propensity	Interest Propensities	Activities & Interests	Sports		Household	Modeled	8,17	17,16	This audience consists of households in the top 20% of a model predicting they have an interest in hunting. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.031	International News	Interest Propensities	Activities & Interests	Media & Entertainment		Household	Modeled	33,09	69,48	This audience consists of households in the top 15-20% of a model predicting an interest in international news. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.065	Live Theater Fans - Propensity	Interest Propensities	Activities & Interests	Media & Entertainment		Household	Modeled	12,82	26,92	This audience consists of households in the top 20% of a model predicting they attend live theater 2+ times per year. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.032	Local News	Interest Propensities	Activities & Interests	Media & Entertainment		Household	Modeled	43,56	91,47	This audience consists of households in the top 15-20% of a model predicting an interest in local news. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.033	Low-End Sporting Equipment Propensity	Interest Propensities	Activities & Interests	Sports	Health & Beauty	Household	Modeled	9,54	20,03	This audience consists of households in the top 20% of a model predicting the likelihood that they spend at least $100 on 2+ items of low-end sporting equipment per year. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.035	Marriage	Interest Propensities	Activities & Interests	Home		Household	Modeled	33,48	70,30	This audience consists of households in the top 15-20% of a model predicting an interest in marriage. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.052	Mobile Phone Only - No Landline - Propensity	Interest Propensities	Activities & Interests	Home		Household	Modeled	4,34	9,11	This audience consists of households in the top 20% of a model predicting they only use a mobile device. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.039	Motorcycles	Interest Propensities	Activities & Interests	Auto		Household	Modeled	45,49	95,53	This audience consists of households in the top 15-20% of a model predicting an interest in motorcycles. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.057	NASCAR Fans - Propensity	Interest Propensities	Activities & Interests	Sports		Household	Modeled	10,24	21,50	This audience consists of households in the top 20% of a model predicting they attended NASCAR races. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.034	National News	Interest Propensities	Activities & Interests	Media & Entertainment		Household	Modeled	44,37	93,17	This audience consists of households in the top 15-20% of a model predicting an interest in national news. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.064	Online Investment / Trading - Propensity	Interest Propensities	Activities & Interests	Financial Services		Household	Modeled	12,98	27,26	This audience consists of households in the top 20% of a model predicting they do online investing and tracking. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.037	Photography	Interest Propensities	Activities & Interests	Media & Entertainment		Household	Modeled	50,66	106,39	This audience consists of households in the top 15-20% of a model predicting an interest in photography. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.038	Pilates/Yoga Propensity	Interest Propensities	Activities & Interests	Sports	Health & Beauty	Household	Modeled	10,49	22,02	This audience consists of households in the top 20% of a model predicting the likelihood that they practice pilates or yoga at least once a month. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.070	Premium Hunting - Propensity	Interest Propensities	Activities & Interests	Sports		Individual	Modeled	9,62	20,21	This audience consists of individualsin the top 20% of a model predicting they have an interest in hunting. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.071	Premium Live Theater Fans - Propensity	Interest Propensities	Activities & Interests	Media & Entertainment		Individual	Modeled	15,27	32,07	This audience consists of individuals in the top 20% of a model predicting they attend live theater 2+ times per year. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.072	Premium Online Investment / Trading - Propensity	Interest Propensities	Activities & Interests	Financial Services		Individual	Modeled	15,45	32,46	This audience consists of individuals in the top 20% of a model predicting they do online investing and tracking. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.074	Premium Wine Lovers - Propensity	Interest Propensities	Activities & Interests	Food & Beverage		Individual	Modeled	13,53	28,41	This audience consists of individuals in the top 20% of a model predicting they drink 5+ glasses of wine per week. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.058	Professional Basketball Fans - Propensity	Interest Propensities	Activities & Interests	Sports		Household	Modeled	6,47	13,58	This audience consists of households in the top 20% of a model predicting they attended professional basketball games in the past year. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.059	Professional Wrestling Fans - Propensity	Interest Propensities	Activities & Interests	Sports		Household	Modeled	2,98	6,26	This audience consists of households in the top 20% of a model predicting they attended professional wrestling events in the past year. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.068	Quality User Generated Content	Interest Propensities	Activities & Interests	Media & Entertainment		Household	Modeled	35,16	73,84	This audience consists of households in the top 15-20% of a model predicting an interest in user generated content. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.040	Real Estate Investor Propensity	Interest Propensities	Activities & Interests	Financial Services		Household	Modeled	10,11	21,22	This audience consists of households in the top 20% of a model predicting the likelihood that they have made investments in real estate. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.041	Satellite Radio Propensity	Interest Propensities	Activities & Interests	Media & Entertainment		Household	Modeled	14,50	30,44	This audience consists of households in the top 20% of a model predicting the likelihood that they listen to satellite radio. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.051	Smart Phone Users - Propensity	Interest Propensities	Activities & Interests	Tech		Household	Modeled	7,77	16,33	This audience consists of households in the top 20% of a model predicting they have a personal smartphone with a bill over $100 per month. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.060	Soccer Fans - Propensity	Interest Propensities	Activities & Interests	Sports		Household	Modeled	6,49	13,63	This audience consists of households in the top 20% of a model predicting they attended soccer matches in the past year. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.042	Social Networking Ad Clicker Propensity	Interest Propensities	Activities & Interests	Media & Entertainment		Household	Modeled	8,47	17,78	This audience consists of households in the top 20% of a model predicting the likelihood that they have clicked on an advertisement while using social networking, photo or video-sharing services in the last 30 days. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.053	Tablet / E-Reader Owner - Propensity	Interest Propensities	Activities & Interests	Tech		Household	Modeled	13,25	27,83	This audience consists of households in the top 20% of a model predicting they own an e-reader or tablet. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.061	Tennis Fans - Propensity	Interest Propensities	Activities & Interests	Sports		Household	Modeled	10,04	21,08	This audience consists of households in the top 20% of a model predicting they attended tennis matches in the past year. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.066	Theme Park Visitor - Propensity	Interest Propensities	Activities & Interests	Travel		Household	Modeled	8,77	18,41	This audience consists of households in the top 20% of a model predicting they visit theme parks 5+ days per year. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.050	UFC	Interest Propensities	Activities & Interests	Sports		Household	Modeled	18,76	39,40	This audience consists of households in the top 15-20% of a model predicting an interest in UFC. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.062	Wine Lovers - Propensity	Interest Propensities	Activities & Interests	Food & Beverage		Household	Modeled	11,57	24,29	This audience consists of households in the top 20% of a model predicting they drink 5+ glasses of wine per week. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
240.235	CarGurus	Interest Propensities	Auto	Auto		Household	Modeled	16,73	35,13	This audience consists of households in the top 15-20% of a model predicting an interest in CarGurus. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.236	Carvana	Interest Propensities	Auto	Auto		Household	Modeled	15,76	33,09	This audience consists of households in the top 15-20% of a model predicting an interest in Carvana. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.278	Vroom	Interest Propensities	Auto	Auto		Household	Modeled	16,73	35,13	This audience consists of households in the top 15-20% of a model predicting an interest in Vroom. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.077	Behr Paint	Interest Propensities	Brands	Home		Household	Modeled	17,61	36,98	This audience consists of households in the top 15-20% of a model predicting an interest in Behr Paint. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.078	Benjamin Moore	Interest Propensities	Brands	Home		Household	Modeled	17,25	36,23	This audience consists of households in the top 15-20% of a model predicting an interest in Benjamin Moore. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.079	Big Box Retail	Interest Propensities	Brands	Retail		Household	Modeled	70,33	147,70	This audience consists of households in the top 15-20% of a model predicting an interest in Big Box Retail. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.080	Frigidaire	Interest Propensities	Brands	Home		Household	Modeled	15,99	33,57	This audience consists of households in the top 15-20% of a model predicting an interest in Frigidaire. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.081	General Electric	Interest Propensities	Brands	Home		Household	Modeled	16,61	34,88	This audience consists of households in the top 15-20% of a model predicting an interest in General Electric. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.089	High-End Tech Brands	Interest Propensities	Brands	Tech		Household	Modeled	38,96	81,82	This audience consists of households in the top 15-20% of a model predicting an interest in High-End Tech Brands. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.082	John Deere	Interest Propensities	Brands	Home		Household	Modeled	15,79	33,15	This audience consists of households in the top 15-20% of a model predicting an interest in John Deere. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.083	Kenmore	Interest Propensities	Brands	Home		Household	Modeled	16,26	34,15	This audience consists of households in the top 15-20% of a model predicting an interest in Kenmore. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.084	La-Z-Boy	Interest Propensities	Brands	Home		Household	Modeled	15,17	31,85	This audience consists of households in the top 15-20% of a model predicting an interest in La-Z-Boy. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.085	LG Electronics	Interest Propensities	Brands	Tech		Household	Modeled	16,05	33,71	This audience consists of households in the top 15-20% of a model predicting an interest in LG Electronics. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.086	Major News Publications	Interest Propensities	Brands	Media & Entertainment		Household	Modeled	34,26	71,95	This audience consists of households in the top 15-20% of a model predicting an interest in Major News Publications. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.087	Panasonic	Interest Propensities	Brands	Tech		Household	Modeled	16,66	34,99	This audience consists of households in the top 15-20% of a model predicting an interest in Panasonic. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.088	Podcasts	Interest Propensities	Brands	Media & Entertainment		Household	Modeled	15,81	33,20	This audience consists of households in the top 15-20% of a model predicting an interest in Podcasts. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.090	Quick Service Restaurants	Interest Propensities	Brands	Food & Beverage		Household	Modeled	68,83	144,55	This audience consists of households in the top 15-20% of a model predicting an interest in Quick Service Restaurants. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.093	Whirlpool	Interest Propensities	Brands	Home		Household	Modeled	15,87	33,33	This audience consists of households in the top 15-20% of a model predicting an interest in Whirlpool. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.097	Barack Obama	Interest Propensities	Celebrities	Politics		Household	Modeled	16,64	34,94	This audience consists of households in the top 15-20% of a model predicting an interest in Barack Obama. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.098	Beyonce	Interest Propensities	Celebrities	Media & Entertainment		Household	Modeled	19,21	40,33	This audience consists of households in the top 15-20% of a model predicting an interest in Beyonce. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.102	Celebrity Fan Gossip	Interest Propensities	Celebrities	Media & Entertainment		Household	Modeled	44,36	93,15	This audience consists of households in the top 15-20% of a model predicting an interest in Celebrity Fan Gossip. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.106	Donald Trump	Interest Propensities	Celebrities	Politics		Household	Modeled	14,69	30,85	This audience consists of households in the top 15-20% of a model predicting an interest in Donald Trump. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.107	Drake	Interest Propensities	Celebrities	Media & Entertainment		Household	Modeled	19,40	40,74	This audience consists of households in the top 15-20% of a model predicting an interest in Drake. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.108	Dwayne Johnson (The Rock)	Interest Propensities	Celebrities	Media & Entertainment		Household	Modeled	18,48	38,81	This audience consists of households in the top 15-20% of a model predicting an interest in Dwayne Johnson (The Rock). The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.110	Hillary Clinton	Interest Propensities	Celebrities	Politics		Household	Modeled	17,43	36,61	This audience consists of households in the top 15-20% of a model predicting an interest in Hillary Clinton. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.114	John Cena	Interest Propensities	Celebrities	Media & Entertainment		Household	Modeled	18,27	38,37	This audience consists of households in the top 15-20% of a model predicting an interest in John Cena. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.116	Justin Bieber	Interest Propensities	Celebrities	Media & Entertainment		Household	Modeled	14,47	30,38	This audience consists of households in the top 15-20% of a model predicting an interest in Justin Bieber. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.120	Lady Gaga	Interest Propensities	Celebrities	Media & Entertainment		Household	Modeled	16,19	34,00	This audience consists of households in the top 15-20% of a model predicting an interest in Lady Gaga. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.127	Pink	Interest Propensities	Celebrities	Media & Entertainment		Household	Modeled	15,66	32,89	This audience consists of households in the top 15-20% of a model predicting an interest in Pink. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.132	Rihanna	Interest Propensities	Celebrities	Media & Entertainment		Household	Modeled	16,84	35,37	This audience consists of households in the top 15-20% of a model predicting an interest in Rihanna. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.134	Taylor Swift	Interest Propensities	Celebrities	Media & Entertainment		Household	Modeled	17,66	37,09	This audience consists of households in the top 15-20% of a model predicting an interest in Taylor Swift. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.137	Alabama Crimson Tide	Interest Propensities	College Teams	Sports		Household	Modeled	16,78	35,24	This audience consists of households in the top 15-20% of a model predicting an interest in Alabama Crimson Tide. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.138	Arizona State Athletics	Interest Propensities	College Teams	Sports		Household	Modeled	18,01	37,82	This audience consists of households in the top 15-20% of a model predicting an interest in Arizona State Athletics. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.139	Clemson Tigers	Interest Propensities	College Teams	Sports		Household	Modeled	15,57	32,69	This audience consists of households in the top 15-20% of a model predicting an interest in Clemson Tigers. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.158	College Basketball Fans - Propensity	Interest Propensities	College Teams	Sports		Household	Modeled	9,27	19,46	This audience consists of households in the top 15-20% of a model predicting an interest in College Basketball Fans - Propensity. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.159	College Football Fans - Propensity	Interest Propensities	College Teams	Sports		Household	Modeled	11,37	23,87	This audience consists of households in the top 15-20% of a model predicting an interest in College Football Fans - Propensity. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.141	Florida Gators	Interest Propensities	College Teams	Sports		Household	Modeled	18,46	38,76	This audience consists of households in the top 15-20% of a model predicting an interest in Florida Gators. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.142	Florida State Seminoles	Interest Propensities	College Teams	Sports		Household	Modeled	16,83	35,35	This audience consists of households in the top 15-20% of a model predicting an interest in Florida State Seminoles. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.145	Louisiana State University Tigers	Interest Propensities	College Teams	Sports		Household	Modeled	17,03	35,77	This audience consists of households in the top 15-20% of a model predicting an interest in Louisiana State University Tigers. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.148	Michigan State Spartans	Interest Propensities	College Teams	Sports		Household	Modeled	19,28	40,49	This audience consists of households in the top 15-20% of a model predicting an interest in Michigan State Spartans. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.149	Michigan Wolverines	Interest Propensities	College Teams	Sports		Household	Modeled	18,26	38,34	This audience consists of households in the top 15-20% of a model predicting an interest in Michigan Wolverines. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.150	Ohio State Buckeyes	Interest Propensities	College Teams	Sports		Household	Modeled	16,48	34,61	This audience consists of households in the top 15-20% of a model predicting an interest in Ohio State Buckeyes. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.153	Southern California Trojans	Interest Propensities	College Teams	Sports		Household	Modeled	16,84	35,36	This audience consists of households in the top 15-20% of a model predicting an interest in Southern California Trojans. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.154	Villanova Wildcats	Interest Propensities	College Teams	Sports		Household	Modeled	18,05	37,90	This audience consists of households in the top 15-20% of a model predicting an interest in Villanova Wildcats. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.157	Wisconsin Badgers	Interest Propensities	College Teams	Sports		Household	Modeled	16,51	34,66	This audience consists of households in the top 15-20% of a model predicting an interest in Wisconsin Badgers. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.161	7UP	Interest Propensities	CPG	CPG		Household	Modeled	16,22	34,07	This audience consists of households in the top 15-20% of a model predicting an interest in 7UP. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.163	Axe	Interest Propensities	CPG	CPG		Household	Modeled	16,80	35,28	This audience consists of households in the top 15-20% of a model predicting an interest in Axe. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.249	Baby Product Buyer - Propensity	Interest Propensities	CPG	CPG	Retail	Household	Modeled	6,42	13,47	This audience consists of households in the top 20% of a model predicting they have a presence of diapers, formula or baby food. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.164	Ben & Jerry's	Interest Propensities	CPG	CPG		Household	Modeled	16,27	34,17	This audience consists of households in the top 15-20% of a model predicting an interest in Ben & Jerry's. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.166	Capri Sun	Interest Propensities	CPG	CPG		Household	Modeled	14,41	30,27	This audience consists of households in the top 15-20% of a model predicting an interest in Capri Sun. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.250	Cat Product Buyer - Propensity	Interest Propensities	CPG	Pet	CPG	Household	Modeled	13,20	27,73	This audience consists of households in the top 20% of a model predicting they spend extra on cat products. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.169	Coca Cola	Interest Propensities	CPG	CPG		Household	Modeled	18,12	38,06	This audience consists of households in the top 15-20% of a model predicting an interest in Coca Cola. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.170	Coffee Mate	Interest Propensities	CPG	CPG		Household	Modeled	15,91	33,41	This audience consists of households in the top 15-20% of a model predicting an interest in Coffee Mate. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.171	Colgate	Interest Propensities	CPG	CPG		Household	Modeled	16,54	34,73	This audience consists of households in the top 15-20% of a model predicting an interest in Colgate. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.247	Coupon Users - Propensity	Interest Propensities	CPG	CPG		Household	Modeled	14,05	29,51	This audience consists of households in the top 20% of a model predicting they have used coupons 12+ times in the past 3 months. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.173	Crest	Interest Propensities	CPG	CPG		Household	Modeled	16,31	34,26	This audience consists of households in the top 15-20% of a model predicting an interest in Crest. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.251	Dog Product Buyer - Propensity	Interest Propensities	CPG	Pet	CPG	Household	Modeled	8,63	18,12	This audience consists of households in the top 20% of a model predicting they spend extra on dog products. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.176	Doritos	Interest Propensities	CPG	CPG		Household	Modeled	17,60	36,96	This audience consists of households in the top 15-20% of a model predicting an interest in Doritos. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.177	Dove	Interest Propensities	CPG	CPG		Household	Modeled	16,47	34,60	This audience consists of households in the top 15-20% of a model predicting an interest in Dove. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.178	Downy	Interest Propensities	CPG	CPG		Household	Modeled	15,71	33,00	This audience consists of households in the top 15-20% of a model predicting an interest in Downy. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.179	Estee Lauder	Interest Propensities	CPG	CPG		Household	Modeled	15,72	33,02	This audience consists of households in the top 15-20% of a model predicting an interest in Estee Lauder. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.180	Fancy Feast	Interest Propensities	CPG	CPG		Household	Modeled	13,75	28,87	This audience consists of households in the top 15-20% of a model predicting an interest in Fancy Feast. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.181	Febreze	Interest Propensities	CPG	CPG		Household	Modeled	15,46	32,47	This audience consists of households in the top 15-20% of a model predicting an interest in Febreze. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.182	Friskies	Interest Propensities	CPG	CPG		Household	Modeled	16,58	34,81	This audience consists of households in the top 15-20% of a model predicting an interest in Friskies. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.183	Frito - Lay snacks	Interest Propensities	CPG	CPG		Household	Modeled	15,76	33,09	This audience consists of households in the top 15-20% of a model predicting an interest in Frito - Lay snacks. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.248	Frozen Dinner Buyers - Propensity	Interest Propensities	CPG	CPG		Household	Modeled	4,30	9,02	This audience consists of households in the top 20% of a model predicting they used frozen complete dinners 9+ times in the past 6 months. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.184	Gain	Interest Propensities	CPG	CPG		Household	Modeled	15,19	31,89	This audience consists of households in the top 15-20% of a model predicting an interest in Gain. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.185	Gatorade	Interest Propensities	CPG	CPG		Household	Modeled	17,53	36,81	This audience consists of households in the top 15-20% of a model predicting an interest in Gatorade. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.186	Gerber Baby Foods	Interest Propensities	CPG	CPG		Household	Modeled	16,12	33,85	This audience consists of households in the top 15-20% of a model predicting an interest in Gerber Baby Foods. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.188	Goya	Interest Propensities	CPG	CPG		Household	Modeled	15,85	33,29	This audience consists of households in the top 15-20% of a model predicting an interest in Goya. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.189	Haagen Dazs	Interest Propensities	CPG	CPG		Household	Modeled	16,26	34,14	This audience consists of households in the top 15-20% of a model predicting an interest in Haagen Dazs. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.191	Head & Shoulders	Interest Propensities	CPG	CPG		Household	Modeled	13,44	28,23	This audience consists of households in the top 15-20% of a model predicting an interest in Head & Shoulders. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.192	Heinz Ketchup	Interest Propensities	CPG	CPG		Household	Modeled	14,47	30,39	This audience consists of households in the top 15-20% of a model predicting an interest in Heinz Ketchup. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.194	Herbal Essences	Interest Propensities	CPG	CPG		Household	Modeled	14,40	30,25	This audience consists of households in the top 15-20% of a model predicting an interest in Herbal Essences. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.195	Hershey	Interest Propensities	CPG	CPG		Household	Modeled	17,56	36,87	This audience consists of households in the top 15-20% of a model predicting an interest in Hershey. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.197	Huggies	Interest Propensities	CPG	CPG		Household	Modeled	15,84	33,26	This audience consists of households in the top 15-20% of a model predicting an interest in Huggies. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.198	IAMS	Interest Propensities	CPG	CPG		Household	Modeled	15,10	31,70	This audience consists of households in the top 15-20% of a model predicting an interest in IAMS. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.201	Kool Aid	Interest Propensities	CPG	CPG		Household	Modeled	15,17	31,86	This audience consists of households in the top 15-20% of a model predicting an interest in Kool Aid. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.202	Kraft Cheeses	Interest Propensities	CPG	CPG		Household	Modeled	17,07	35,85	This audience consists of households in the top 15-20% of a model predicting an interest in Kraft Cheeses. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.203	Lean Cuisine	Interest Propensities	CPG	CPG		Household	Modeled	16,90	35,50	This audience consists of households in the top 15-20% of a model predicting an interest in Lean Cuisine. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.205	L'oreal	Interest Propensities	CPG	CPG		Household	Modeled	15,27	32,07	This audience consists of households in the top 15-20% of a model predicting an interest in L'oreal. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.206	Lunchables	Interest Propensities	CPG	CPG		Household	Modeled	16,73	35,13	This audience consists of households in the top 15-20% of a model predicting an interest in Lunchables. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.207	Luvs Diapers	Interest Propensities	CPG	CPG		Household	Modeled	15,65	32,86	This audience consists of households in the top 15-20% of a model predicting an interest in Luvs Diapers. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.208	Maxwell House	Interest Propensities	CPG	CPG		Household	Modeled	15,03	31,57	This audience consists of households in the top 15-20% of a model predicting an interest in Maxwell House. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.209	Maybelline	Interest Propensities	CPG	CPG		Household	Modeled	14,88	31,24	This audience consists of households in the top 15-20% of a model predicting an interest in Maybelline. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.210	Mountain Dew	Interest Propensities	CPG	CPG		Household	Modeled	16,58	34,82	This audience consists of households in the top 15-20% of a model predicting an interest in Mountain Dew. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.211	Mr. Clean	Interest Propensities	CPG	CPG		Household	Modeled	17,15	36,02	This audience consists of households in the top 15-20% of a model predicting an interest in Mr. Clean. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.214	Nestle Candy	Interest Propensities	CPG	CPG		Household	Modeled	16,77	35,21	This audience consists of households in the top 15-20% of a model predicting an interest in Nestle Candy. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.215	Nestle Pure Life	Interest Propensities	CPG	CPG		Household	Modeled	15,38	32,29	This audience consists of households in the top 15-20% of a model predicting an interest in Nestle Pure Life. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.216	Neutrogena	Interest Propensities	CPG	CPG		Household	Modeled	18,78	39,44	This audience consists of households in the top 15-20% of a model predicting an interest in Neutrogena. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.217	Nexxus	Interest Propensities	CPG	CPG		Household	Modeled	14,89	31,27	This audience consists of households in the top 15-20% of a model predicting an interest in Nexxus. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.218	Nivea	Interest Propensities	CPG	CPG		Household	Modeled	15,54	32,63	This audience consists of households in the top 15-20% of a model predicting an interest in Nivea. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.219	Olay	Interest Propensities	CPG	CPG		Household	Modeled	15,91	33,41	This audience consists of households in the top 15-20% of a model predicting an interest in Olay. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.220	Old Spice	Interest Propensities	CPG	CPG		Household	Modeled	16,69	35,06	This audience consists of households in the top 15-20% of a model predicting an interest in Old Spice. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.221	Oreo	Interest Propensities	CPG	CPG		Household	Modeled	18,89	39,67	This audience consists of households in the top 15-20% of a model predicting an interest in Oreo. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.222	Oscar Meyer	Interest Propensities	CPG	CPG		Household	Modeled	17,24	36,20	This audience consists of households in the top 15-20% of a model predicting an interest in Oscar Meyer. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.223	Pampers	Interest Propensities	CPG	CPG		Household	Modeled	16,03	33,66	This audience consists of households in the top 15-20% of a model predicting an interest in Pampers. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.224	Pantene	Interest Propensities	CPG	CPG		Household	Modeled	14,42	30,28	This audience consists of households in the top 15-20% of a model predicting an interest in Pantene. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.225	Pepsi	Interest Propensities	CPG	CPG		Household	Modeled	17,27	36,27	This audience consists of households in the top 15-20% of a model predicting an interest in Pepsi. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.226	Pepto-Bismol	Interest Propensities	CPG	CPG		Household	Modeled	15,04	31,59	This audience consists of households in the top 15-20% of a model predicting an interest in Pepto-Bismol. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.227	Planters Nuts	Interest Propensities	CPG	CPG		Household	Modeled	18,77	39,42	This audience consists of households in the top 15-20% of a model predicting an interest in Planters Nuts. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.228	Poland Spring	Interest Propensities	CPG	CPG		Household	Modeled	14,49	30,43	This audience consists of households in the top 15-20% of a model predicting an interest in Poland Spring. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.252	Premium Cat Product Buyer - Propensity	Interest Propensities	CPG	Pet	CPG	Individual	Modeled	15,61	32,78	This audience consists of individuals in the top 20% of a model predicting they spend extra on cat products. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.253	Premium Coupon Users - Propensity	Interest Propensities	CPG	CPG		Individual	Modeled	16,64	34,95	This audience consists of individuals in the top 20% of a model predicting they have used coupons 12+ times in the past 3 months. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.254	Premium Dog Product Buyer - Propensity	Interest Propensities	CPG	Pet	CPG	Individual	Modeled	10,11	21,24	This audience consists of individuals in the top 20% of a model predicting they spend extra on dog products. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.230	Purina	Interest Propensities	CPG	CPG		Household	Modeled	15,05	31,60	This audience consists of households in the top 15-20% of a model predicting an interest in Purina. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.235	Secret	Interest Propensities	CPG	CPG		Household	Modeled	14,23	29,89	This audience consists of households in the top 15-20% of a model predicting an interest in Secret. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.236	Sprite	Interest Propensities	CPG	CPG		Household	Modeled	17,29	36,31	This audience consists of households in the top 15-20% of a model predicting an interest in Sprite. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.237	Stouffer's	Interest Propensities	CPG	CPG		Household	Modeled	14,53	30,50	This audience consists of households in the top 15-20% of a model predicting an interest in Stouffer's. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.238	Suave	Interest Propensities	CPG	CPG		Household	Modeled	16,00	33,59	This audience consists of households in the top 15-20% of a model predicting an interest in Suave. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.239	Swiffer	Interest Propensities	CPG	CPG		Household	Modeled	15,96	33,51	This audience consists of households in the top 15-20% of a model predicting an interest in Swiffer. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.240	Tide	Interest Propensities	CPG	CPG		Household	Modeled	16,89	35,47	This audience consists of households in the top 15-20% of a model predicting an interest in Tide. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.241	Tom's of Maine	Interest Propensities	CPG	CPG		Household	Modeled	15,89	33,36	This audience consists of households in the top 15-20% of a model predicting an interest in Tom's of Maine. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.244	Tropicana	Interest Propensities	CPG	CPG		Household	Modeled	15,33	32,19	This audience consists of households in the top 15-20% of a model predicting an interest in Tropicana. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.427	Binance	Interest Propensities	Cryptocurrencies	Financial Services		Household	Modeled	18,39	38,63	This audience consists of households in the top 15-20% of a model predicting an interest in Binance. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.414	Bitcoin Cash	Interest Propensities	Cryptocurrencies	Tech		Household	Modeled	15,95	33,50	This audience consists of households in the top 15-20% of a model predicting an interest in Bitcoin Cash. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.422	Cardano	Interest Propensities	Cryptocurrencies	Tech		Household	Modeled	25,96	54,51	This audience consists of households in the top 15-20% of a model predicting an interest in Cardano. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.417	Coinbase	Interest Propensities	Cryptocurrencies	Financial Services		Household	Modeled	21,50	45,16	This audience consists of households in the top 15-20% of a model predicting an interest in Coinbase. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.418	Crypto.com	Interest Propensities	Cryptocurrencies	Financial Services		Household	Modeled	15,42	32,37	This audience consists of households in the top 15-20% of a model predicting an interest in Crypto.com. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.420	Dogecoin	Interest Propensities	Cryptocurrencies	Tech		Household	Modeled	22,71	47,68	This audience consists of households in the top 15-20% of a model predicting an interest in Doge Coin. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.415	Ethereum	Interest Propensities	Cryptocurrencies	Tech		Household	Modeled	16,33	34,28	This audience consists of households in the top 15-20% of a model predicting an interest in Ethereum. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.421	Litecoin	Interest Propensities	Cryptocurrencies	Tech		Household	Modeled	21,25	44,62	This audience consists of households in the top 15-20% of a model predicting an interest in Litecoin. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.425	Monero	Interest Propensities	Cryptocurrencies	Tech		Household	Modeled	15,76	33,10	This audience consists of households in the top 15-20% of a model predicting an interest in Monero. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.416	NFT	Interest Propensities	Cryptocurrencies	Tech		Household	Modeled	8,58	18,02	This audience consists of households in the top 15-20% of a model predicting an interest in NFTs. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.423	Polkadot	Interest Propensities	Cryptocurrencies	Tech		Household	Modeled	24,85	52,19	This audience consists of households in the top 15-20% of a model predicting an interest in Polkadot. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.419	Solana	Interest Propensities	Cryptocurrencies	Tech		Household	Modeled	15,11	31,73	This audience consists of households in the top 15-20% of a model predicting an interest in Solana. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.426	StellarOrg	Interest Propensities	Cryptocurrencies	Financial Services		Household	Modeled	13,19	27,71	This audience consists of households in the top 15-20% of a model predicting an interest in StellarOrg. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.424	Tether	Interest Propensities	Cryptocurrencies	Tech		Household	Modeled	31,44	66,02	This audience consists of households in the top 15-20% of a model predicting an interest in Tether. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.223	Android	Interest Propensities	Electronics	Tech		Household	Modeled	15,89	33,38	This audience consists of households in the top 15-20% of a model predicting an interest in Android. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.225	Apple Watch	Interest Propensities	Electronics	Tech		Household	Modeled	16,13	33,88	This audience consists of households in the top 15-20% of a model predicting an interest in Apple Watch. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.253	iPhone	Interest Propensities	Electronics	Tech		Household	Modeled	15,70	32,97	This audience consists of households in the top 15-20% of a model predicting an interest in iPhone. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.256	Anime	Interest Propensities	Events/Shows	Media & Entertainment		Household	Modeled	17,95	37,69	This audience consists of households in the top 15-20% of a model predicting an interest in Anime. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.257	ComiCon	Interest Propensities	Events/Shows	Media & Entertainment		Household	Modeled	18,08	37,96	This audience consists of households in the top 15-20% of a model predicting an interest in ComiCon. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.260	International Builders' Show (NAHB)	Interest Propensities	Events/Shows	Media & Entertainment		Household	Modeled	15,56	32,68	This audience consists of households in the top 15-20% of a model predicting an interest in International Builders' Show (NAHB). The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.262	Magic Las Vegas	Interest Propensities	Events/Shows	Media & Entertainment		Household	Modeled	17,47	36,68	This audience consists of households in the top 15-20% of a model predicting an interest in Magic Las Vegas. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.263	National Automobile Dealers Association	Interest Propensities	Events/Shows	Media & Entertainment		Household	Modeled	15,89	33,37	This audience consists of households in the top 15-20% of a model predicting an interest in National Automobile Dealers Association. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.264	New York Auto Show	Interest Propensities	Events/Shows	Media & Entertainment		Household	Modeled	14,66	30,79	This audience consists of households in the top 15-20% of a model predicting an interest in New York Auto Show. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.227	Bank of America	Interest Propensities	Financial	Financial Services		Household	Modeled	16,27	34,16	This audience consists of households in the top 15-20% of a model predicting an interest in Bank of America. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.238	Chase Bank	Interest Propensities	Financial	Financial Services		Household	Modeled	16,41	34,46	This audience consists of households in the top 15-20% of a model predicting an interest in Chase Bank. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.240	Citibank	Interest Propensities	Financial	Financial Services		Household	Modeled	15,74	33,05	This audience consists of households in the top 15-20% of a model predicting an interest in Citibank. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.279	Zelle	Interest Propensities	Financial	Financial Services		Household	Modeled	15,75	33,07	This audience consists of households in the top 15-20% of a model predicting an interest in Zelle. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.255	Jenny Craig	Interest Propensities	Health & Beauty	Health & Beauty		Household	Modeled	15,52	32,60	This audience consists of households in the top 15-20% of a model predicting an interest in Jenny Craig. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.243	Life Time Fitness	Interest Propensities	Health & Beauty	Fitness		Household	Modeled	17,26	36,25	This audience consists of households in the top 15-20% of a model predicting an interest in Life Time Fitness. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.258	Medifast	Interest Propensities	Health & Beauty	Health & Beauty		Household	Modeled	16,36	34,35	This audience consists of households in the top 15-20% of a model predicting an interest in Medifast. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.455	Arthritis	Interest Propensities	Health Ailment	Health & Beauty		Household	Modeled	47,85	100,48	This audience consists of households in the top 15-20% of a model predicting an interest in Arthritis. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.462	Asthma	Interest Propensities	Health Ailment	Health & Beauty		Household	Modeled	29,67	62,31	This audience consists of households in the top 15-20% of a model predicting an interest in Asthma. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.459	Autoimmune	Interest Propensities	Health Ailment	Health & Beauty		Household	Modeled	59,83	125,63	This audience consists of households in the top 15-20% of a model predicting an interest in Autoimmune. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.466	Bronchitis	Interest Propensities	Health Ailment	Health & Beauty		Household	Modeled	43,91	92,22	This audience consists of households in the top 15-20% of a model predicting an interest in Bronchitis. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.461	Cirrhosis	Interest Propensities	Health Ailment	Health & Beauty		Household	Modeled	13,32	27,96	This audience consists of households in the top 15-20% of a model predicting an interest in Cirrhosis. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.467	Crohn's	Interest Propensities	Health Ailment	Health & Beauty		Household	Modeled	33,65	70,68	This audience consists of households in the top 15-20% of a model predicting an interest in Crohn's. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.458	Cystic Fibrosis	Interest Propensities	Health Ailment	Health & Beauty		Household	Modeled	39,31	82,54	This audience consists of households in the top 15-20% of a model predicting an interest in Cystic Fibrosis. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.468	Dystonia	Interest Propensities	Health Ailment	Health & Beauty		Household	Modeled	45,00	94,50	This audience consists of households in the top 15-20% of a model predicting an interest in Dystonia. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.463	Hearing Loss	Interest Propensities	Health Ailment	Health & Beauty		Household	Modeled	42,31	88,85	This audience consists of households in the top 15-20% of a model predicting an interest in Hearing Loss. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.456	Heart Health	Interest Propensities	Health Ailment	Health & Beauty		Household	Modeled	47,04	98,79	This audience consists of households in the top 15-20% of a model predicting an interest in Heart Health. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.454	Migraine	Interest Propensities	Health Ailment	Health & Beauty		Household	Modeled	50,68	106,43	This audience consists of households in the top 15-20% of a model predicting an interest in Migraines. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.457	Multiple Sclerosis	Interest Propensities	Health Ailment	Health & Beauty		Household	Modeled	55,57	116,70	This audience consists of households in the top 15-20% of a model predicting an interest in Multiple Sclerosis. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.453	Osteoporosis	Interest Propensities	Health Ailment	Health & Beauty		Household	Modeled	28,02	58,85	This audience consists of households in the top 15-20% of a model predicting an interest in Osteoporosis. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.460	Psoriasis	Interest Propensities	Health Ailment	Health & Beauty		Household	Modeled	34,35	72,13	This audience consists of households in the top 15-20% of a model predicting an interest in Psoriasis. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.465	Tuberculosis	Interest Propensities	Health Ailment	Health & Beauty		Household	Modeled	21,26	44,66	This audience consists of households in the top 15-20% of a model predicting an interest in Tuberculosis. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.464	Vision Loss	Interest Propensities	Health Ailment	Health & Beauty		Household	Modeled	46,04	96,68	This audience consists of households in the top 15-20% of a model predicting an interest in Vision Loss. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.268	Halloween	Interest Propensities	Holidays	Holiday		Household	Modeled	16,14	33,89	This audience consists of households in the top 15-20% of a model predicting an interest in Halloween. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.269	Last Minute Holiday Shoppers	Interest Propensities	Holidays	Holiday		Household	Modeled	15,73	33,03	This audience consists of households in the top 15-20% of a model predicting an interest in Last Minute Holiday Shoppers. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.270	Pre-Thanksgiving Shoppers	Interest Propensities	Holidays	Holiday		Household	Modeled	17,45	36,64	This audience consists of households in the top 15-20% of a model predicting an interest in Pre-Thanksgiving Shoppers. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.271	St. Patrick's Day	Interest Propensities	Holidays	Holiday		Household	Modeled	18,11	38,02	This audience consists of households in the top 15-20% of a model predicting an interest in St. Patrick's Day. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.272	Valentine's Day	Interest Propensities	Holidays	Holiday		Household	Modeled	15,88	33,35	This audience consists of households in the top 15-20% of a model predicting an interest in Valentine's Day. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.092	Sherwin Williams	Interest Propensities	Home	Home		Household	Modeled	17,21	36,14	This audience consists of households in the top 15-20% of a model predicting an interest in Sherwin Williams. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.274	Aetna Group	Interest Propensities	Insurance	Financial Services		Household	Modeled	43,67	91,70	This audience consists of households in the top 15-20% of a model predicting an interest in Aetna Group. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.275	Anthem	Interest Propensities	Insurance	Financial Services		Household	Modeled	39,56	83,07	This audience consists of households in the top 15-20% of a model predicting an interest in Anthem. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.276	Cigna Health Group	Interest Propensities	Insurance	Financial Services		Household	Modeled	41,80	87,79	This audience consists of households in the top 15-20% of a model predicting an interest in Cigna Health Group. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.288	Health Insurance - Propensity	Interest Propensities	Insurance	Financial Services		Household	Modeled	11,89	24,97	This audience consists of households in the top 20% of a model predicting they have purchased health insurance via an agent, direct or online. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.277	Humana	Interest Propensities	Insurance	Financial Services		Household	Modeled	41,28	86,69	This audience consists of households in the top 15-20% of a model predicting an interest in Humana. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.256	Lemonaid Health	Interest Propensities	Insurance	Financial Services		Household	Modeled	16,51	34,66	This audience consists of households in the top 15-20% of a model predicting an interest in Lemonaid Health. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.289	Life Insurance Buyers - Propensity	Interest Propensities	Insurance	Financial Services		Household	Modeled	10,92	22,92	This audience consists of households in the top 20% of a model predicting they have life insurance via an agent. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.279	Lincoln Heritage	Interest Propensities	Insurance	Financial Services		Household	Modeled	48,67	102,20	This audience consists of households in the top 15-20% of a model predicting an interest in Lincoln Heritage. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.280	MassMutual	Interest Propensities	Insurance	Financial Services		Household	Modeled	55,15	115,82	This audience consists of households in the top 15-20% of a model predicting an interest in MassMutual. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.281	MetLife	Interest Propensities	Insurance	Financial Services		Household	Modeled	46,59	97,85	This audience consists of households in the top 15-20% of a model predicting an interest in MetLife. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.283	New York Life	Interest Propensities	Insurance	Financial Services		Household	Modeled	39,13	82,17	This audience consists of households in the top 15-20% of a model predicting an interest in New York Life. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.284	Northwestern Mutual	Interest Propensities	Insurance	Financial Services		Household	Modeled	34,77	73,02	This audience consists of households in the top 15-20% of a model predicting an interest in Northwestern Mutual. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.291	Premium Health Insurance - Propensity	Interest Propensities	Insurance	Financial Services		Individual	Modeled	14,02	29,44	This audience consists of individuals in the top 20% of a model predicting they have purchased health insurance via an agent, direct or online. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.292	Premium Life Insurance Buyers - Propensity	Interest Propensities	Insurance	Financial Services		Individual	Modeled	13,11	27,54	This audience consists of individuals in the top 20% of a model predicting they have life insurance via an agent. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.293	Premium Safety & Security Insurance Buyers - Propensity	Interest Propensities	Insurance	Financial Services		Individual	Modeled	16,15	33,92	This audience consists of individuals in the top 20% of a model predicting they purchase insurance for travel, identity theft, disability, accidental, life and/or joined an auto club. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.285	Prudential	Interest Propensities	Insurance	Financial Services		Household	Modeled	53,64	112,64	This audience consists of households in the top 15-20% of a model predicting an interest in Prudential. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.290	Safety / Security Insurance Buyers - Propensity	Interest Propensities	Insurance	Financial Services		Household	Modeled	13,47	28,28	This audience consists of households in the top 20% of a model predicting they purchase insurance for travel, identity theft, disability, accidental, life and/or joined an auto club. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.286	Transamerica	Interest Propensities	Insurance	Financial Services		Household	Modeled	40,09	84,19	This audience consists of households in the top 15-20% of a model predicting an interest in Transamerica. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.287	Unitedhealth Group	Interest Propensities	Insurance	Financial Services		Household	Modeled	38,17	80,17	This audience consists of households in the top 15-20% of a model predicting an interest in Unitedhealth Group. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.296	Against Right to Work	Interest Propensities	Issues & Causes	Politics	Non-Profit	Household	Modeled	16,10	33,80	This audience consists of households in the top 15-20% of a model predicting an interest in Against Right to Work. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.297	Against School Choice	Interest Propensities	Issues & Causes	Politics	Non-Profit	Household	Modeled	19,09	40,09	This audience consists of households in the top 15-20% of a model predicting an interest in Against School Choice. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.299	Against The Muslim Ban	Interest Propensities	Issues & Causes	Politics	Non-Profit	Household	Modeled	17,00	35,71	This audience consists of households in the top 15-20% of a model predicting an interest in Against The Muslim Ban. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.300	Against Voter Fraud (Fighting Voter Fraud)	Interest Propensities	Issues & Causes	Politics	Non-Profit	Household	Modeled	17,59	36,94	This audience consists of households in the top 15-20% of a model predicting an interest in Against Voter Fraud (Fighting Voter Fraud). The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.326	Border Security	Interest Propensities	Issues & Causes	Politics		Household	Modeled	39,49	82,92	This audience consists of households in the top 15-20% of a model predicting an interest in Border Security. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.301	Campaign Finance Reform (Non-Partisan)	Interest Propensities	Issues & Causes	Politics	Non-Profit	Household	Modeled	16,03	33,67	This audience consists of households in the top 15-20% of a model predicting an interest in Campaign Finance Reform (Non-Partisan). The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.302	Citizenship-Immigration Reform	Interest Propensities	Issues & Causes	Politics	Non-Profit	Household	Modeled	17,38	36,50	This audience consists of households in the top 15-20% of a model predicting an interest in Citizenship-Immigration Reform. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.304	Climate Change (Protect the Planet)	Interest Propensities	Issues & Causes	Politics	Non-Profit	Household	Modeled	15,29	32,10	This audience consists of households in the top 15-20% of a model predicting an interest in Climate Change (Protect the Planet). The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.329	Crime	Interest Propensities	Issues & Causes	Politics		Household	Modeled	29,88	62,74	This audience consists of households in the top 15-20% of a model predicting an interest in crime. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.306	Environmental & Wildlife Conservation	Interest Propensities	Issues & Causes	Politics	Non-Profit	Household	Modeled	16,38	34,40	This audience consists of households in the top 15-20% of a model predicting an interest in Environmental & Wildlife Conservation. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.307	Gun Laws (End Gun Violence)	Interest Propensities	Issues & Causes	Politics	Non-Profit	Household	Modeled	15,67	32,91	This audience consists of households in the top 15-20% of a model predicting an interest in Gun Laws (End Gun Violence). The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.308	Gun Rights	Interest Propensities	Issues & Causes	Politics	Non-Profit	Household	Modeled	20,41	42,85	This audience consists of households in the top 15-20% of a model predicting an interest in Gun Rights. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.310	Humanitarian-Civic	Interest Propensities	Issues & Causes	Politics	Non-Profit	Household	Modeled	18,57	38,99	This audience consists of households in the top 15-20% of a model predicting an interest in Humanitarian-Civic. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.311	Humanitarian-Intervention	Interest Propensities	Issues & Causes	Politics	Non-Profit	Household	Modeled	17,60	36,95	This audience consists of households in the top 15-20% of a model predicting an interest in Humanitarian-Intervention. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.325	Inflation	Interest Propensities	Issues & Causes	Politics		Household	Modeled	39,36	82,66	This audience consists of households in the top 15-20% of a model predicting an interest in inflation. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.312	LGBT Rights	Interest Propensities	Issues & Causes	Politics	Non-Profit	Household	Modeled	15,29	32,11	This audience consists of households in the top 15-20% of a model predicting an interest in LGBTQ Rights. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.313	Marijuana Legalization	Interest Propensities	Issues & Causes	Politics	Non-Profit	Household	Modeled	16,00	33,61	This audience consists of households in the top 15-20% of a model predicting an interest in Marijuana Legalization. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.314	National Security/Disarmament	Interest Propensities	Issues & Causes	Politics	Non-Profit	Household	Modeled	15,45	32,44	This audience consists of households in the top 15-20% of a model predicting an interest in National Security/Disarmament. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.315	Opioid Crisis	Interest Propensities	Issues & Causes	Politics	Non-Profit	Household	Modeled	15,74	33,06	This audience consists of households in the top 15-20% of a model predicting an interest in Opioid Crisis. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.316	Pro Affordable Care Act	Interest Propensities	Issues & Causes	Politics	Non-Profit	Household	Modeled	16,14	33,90	This audience consists of households in the top 15-20% of a model predicting an interest in Pro Affordable Care Act. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.317	Pro Choice	Interest Propensities	Issues & Causes	Politics	Non-Profit	Household	Modeled	19,29	40,52	This audience consists of households in the top 15-20% of a model predicting an interest in Pro Choice. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.318	Pro Education Reform	Interest Propensities	Issues & Causes	Politics	Non-Profit	Household	Modeled	18,53	38,91	This audience consists of households in the top 15-20% of a model predicting an interest in Pro Education Reform. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.319	Pro Life	Interest Propensities	Issues & Causes	Politics	Non-Profit	Household	Modeled	15,96	33,52	This audience consists of households in the top 15-20% of a model predicting an interest in Pro Life. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.320	Pro Right To Work	Interest Propensities	Issues & Causes	Politics	Non-Profit	Household	Modeled	15,62	32,79	This audience consists of households in the top 15-20% of a model predicting an interest in Pro Right To Work. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.321	Pro School Choice	Interest Propensities	Issues & Causes	Politics	Non-Profit	Household	Modeled	15,71	32,99	This audience consists of households in the top 15-20% of a model predicting an interest in Pro School Choice. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.322	Social Conservatives	Interest Propensities	Issues & Causes	Politics	Non-Profit	Household	Modeled	15,92	33,44	This audience consists of households in the top 15-20% of a model predicting an interest in Social Conservatives. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.323	Social Liberals	Interest Propensities	Issues & Causes	Politics	Non-Profit	Household	Modeled	18,53	38,91	This audience consists of households in the top 15-20% of a model predicting an interest in Social Liberals. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.330	Social Security & Medicare	Interest Propensities	Issues & Causes	Politics		Household	Modeled	43,40	91,14	This audience consists of households in the top 15-20% of a model predicting an interest in Social Security & Medicare. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.325	Support Our Veterans	Interest Propensities	Issues & Causes	Politics	Non-Profit	Household	Modeled	17,15	36,02	This audience consists of households in the top 15-20% of a model predicting an interest in Support Our Veterans. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.327	Ukraine War	Interest Propensities	Issues & Causes	Politics		Household	Modeled	20,02	42,03	This audience consists of households in the top 15-20% of a model predicting an interest in the Ukraine War. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.328	US Foreign Policy	Interest Propensities	Issues & Causes	Politics		Household	Modeled	21,01	44,11	This audience consists of households in the top 15-20% of a model predicting an interest in US Foreign Policy. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.076	Audible	Interest Propensities	Media & Entertainment	Tech	Media & Entertainment	Household	Modeled	16,99	35,69	This audience consists of households in the top 15-20% of a model predicting an interest in Audible. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.327	Air Force	Interest Propensities	Military	Military		Household	Modeled	18,92	39,73	This audience consists of households in the top 15-20% of a model predicting an interest in Air Force. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.328	Army	Interest Propensities	Military	Military		Household	Modeled	19,02	39,94	This audience consists of households in the top 15-20% of a model predicting an interest in Army. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.329	Coast Guard	Interest Propensities	Military	Military		Household	Modeled	18,27	38,37	This audience consists of households in the top 15-20% of a model predicting an interest in Coast Guard. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.330	Marines	Interest Propensities	Military	Military		Household	Modeled	18,73	39,34	This audience consists of households in the top 15-20% of a model predicting an interest in Marines. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.331	Military Families	Interest Propensities	Military	Military		Household	Modeled	14,27	29,96	This audience consists of households in the top 15-20% of a model predicting an interest in Military Families. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.332	National Guard	Interest Propensities	Military	Military		Household	Modeled	18,50	38,85	This audience consists of households in the top 15-20% of a model predicting an interest in National Guard. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.333	Navy	Interest Propensities	Military	Military		Household	Modeled	18,54	38,94	This audience consists of households in the top 15-20% of a model predicting an interest in Navy. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.334	Veteran Associations	Interest Propensities	Military	Military		Household	Modeled	16,86	35,41	This audience consists of households in the top 15-20% of a model predicting an interest in Veteran Associations. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.336	Arizona Diamondbacks	Interest Propensities	MLB	Sports		Household	Modeled	15,66	32,88	This audience consists of households in the top 15-20% of a model predicting an interest in Arizona Diamondbacks. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.337	Atlanta Braves	Interest Propensities	MLB	Sports		Household	Modeled	14,90	31,29	This audience consists of households in the top 15-20% of a model predicting an interest in Atlanta Braves. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.338	Baltimore Orioles	Interest Propensities	MLB	Sports		Household	Modeled	14,43	30,31	This audience consists of households in the top 15-20% of a model predicting an interest in Baltimore Orioles. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.339	Boston Red Sox	Interest Propensities	MLB	Sports		Household	Modeled	18,06	37,93	This audience consists of households in the top 15-20% of a model predicting an interest in Boston Red Sox. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.340	Chicago Cubs	Interest Propensities	MLB	Sports		Household	Modeled	19,10	40,11	This audience consists of households in the top 15-20% of a model predicting an interest in Chicago Cubs. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.341	Chicago White Sox	Interest Propensities	MLB	Sports		Household	Modeled	14,70	30,87	This audience consists of households in the top 15-20% of a model predicting an interest in Chicago White Sox. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.342	Cincinnati Reds	Interest Propensities	MLB	Sports		Household	Modeled	14,38	30,19	This audience consists of households in the top 15-20% of a model predicting an interest in Cincinnati Reds. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.343	Cleveland Guardians	Interest Propensities	MLB	Sports		Household	Modeled	16,67	35,02	This audience consists of households in the top 15-20% of a model predicting an interest in Cleveland Indians. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.344	Colorado Rockies	Interest Propensities	MLB	Sports		Household	Modeled	15,11	31,73	This audience consists of households in the top 15-20% of a model predicting an interest in Colorado Rockies. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.345	Detroit Tigers	Interest Propensities	MLB	Sports		Household	Modeled	18,64	39,14	This audience consists of households in the top 15-20% of a model predicting an interest in Detroit Tigers. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.346	Houston Astros	Interest Propensities	MLB	Sports		Household	Modeled	17,54	36,84	This audience consists of households in the top 15-20% of a model predicting an interest in Houston Astros. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.347	Kansas City Royals	Interest Propensities	MLB	Sports		Household	Modeled	14,56	30,58	This audience consists of households in the top 15-20% of a model predicting an interest in Kansas City Royals. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.348	LA Dodgers	Interest Propensities	MLB	Sports		Household	Modeled	17,47	36,69	This audience consists of households in the top 15-20% of a model predicting an interest in LA Dodgers. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.349	Los Angeles Angels	Interest Propensities	MLB	Sports		Household	Modeled	14,12	29,64	This audience consists of households in the top 15-20% of a model predicting an interest in Los Angeles Angels. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.350	Miami Marlins	Interest Propensities	MLB	Sports		Household	Modeled	15,88	33,36	This audience consists of households in the top 15-20% of a model predicting an interest in Miami Marlins. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.351	Milwaukee Brewers	Interest Propensities	MLB	Sports		Household	Modeled	14,06	29,52	This audience consists of households in the top 15-20% of a model predicting an interest in Milwaukee Brewers. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.352	Minnesota Twins	Interest Propensities	MLB	Sports		Household	Modeled	14,57	30,60	This audience consists of households in the top 15-20% of a model predicting an interest in Minnesota Twins. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.353	NY Mets	Interest Propensities	MLB	Sports		Household	Modeled	14,59	30,63	This audience consists of households in the top 15-20% of a model predicting an interest in NY Mets. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.354	NY Yankees	Interest Propensities	MLB	Sports		Household	Modeled	17,71	37,20	This audience consists of households in the top 15-20% of a model predicting an interest in NY Yankees. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.355	Oakland A's	Interest Propensities	MLB	Sports		Household	Modeled	14,75	30,97	This audience consists of households in the top 15-20% of a model predicting an interest in Oakland A's. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.356	Philadelphia Phillies	Interest Propensities	MLB	Sports		Household	Modeled	19,78	41,54	This audience consists of households in the top 15-20% of a model predicting an interest in Philadelphia Phillies. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.357	Pittsburgh Pirates	Interest Propensities	MLB	Sports		Household	Modeled	12,96	27,21	This audience consists of households in the top 15-20% of a model predicting an interest in Pittsburgh Pirates. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.366	Professional Baseball Fans - Propensity	Interest Propensities	MLB	Sports		Household	Modeled	7,44	15,63	This audience consists of households in the top 20% of a model predicting they have attended baseball games in the past year. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.358	San Diego Padres	Interest Propensities	MLB	Sports		Household	Modeled	14,88	31,25	This audience consists of households in the top 15-20% of a model predicting an interest in San Diego Padres. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.359	San Francisco Giants	Interest Propensities	MLB	Sports		Household	Modeled	18,48	38,80	This audience consists of households in the top 15-20% of a model predicting an interest in San Francisco Giants. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.360	Seattle Mariners	Interest Propensities	MLB	Sports		Household	Modeled	15,77	33,11	This audience consists of households in the top 15-20% of a model predicting an interest in Seattle Mariners. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.361	St. Louis Cardinals	Interest Propensities	MLB	Sports		Household	Modeled	14,34	30,12	This audience consists of households in the top 15-20% of a model predicting an interest in St. Louis Cardinals. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.362	Tampa Bay Rays	Interest Propensities	MLB	Sports		Household	Modeled	15,19	31,90	This audience consists of households in the top 15-20% of a model predicting an interest in Tampa Bay Rays. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.363	Texas Rangers	Interest Propensities	MLB	Sports		Household	Modeled	14,72	30,91	This audience consists of households in the top 15-20% of a model predicting an interest in Texas Rangers. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.365	Washington Nationals	Interest Propensities	MLB	Sports		Household	Modeled	14,45	30,35	This audience consists of households in the top 15-20% of a model predicting an interest in Washington Nationals. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.370	Batman	Interest Propensities	Movies	Media & Entertainment		Household	Modeled	44,06	92,52	This audience consists of households in the top 15-20% of a model predicting an interest in Batman. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.372	Black Widow	Interest Propensities	Movies	Media & Entertainment		Household	Modeled	31,29	65,71	This audience consists of households in the top 15-20% of a model predicting an interest in Black Widow. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.373	Cars	Interest Propensities	Movies	Media & Entertainment		Household	Modeled	20,18	42,37	This audience consists of households in the top 15-20% of a model predicting an interest in Cars. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.374	Cinderella	Interest Propensities	Movies	Media & Entertainment		Household	Modeled	13,73	28,82	This audience consists of households in the top 15-20% of a model predicting an interest in Cinderella. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.376	DC Comics Movies	Interest Propensities	Movies	Media & Entertainment		Household	Modeled	50,02	105,04	This audience consists of households in the top 15-20% of a model predicting an interest in DC Comic movies. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.378	Disney Live Action Movies	Interest Propensities	Movies	Media & Entertainment		Household	Modeled	46,51	97,68	This audience consists of households in the top 15-20% of a model predicting an interest in Disney Live Action movies. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.381	Fantastic Four	Interest Propensities	Movies	Media & Entertainment		Household	Modeled	18,84	39,57	This audience consists of households in the top 15-20% of a model predicting an interest in Fantastic Four. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.382	Frozen	Interest Propensities	Movies	Media & Entertainment		Household	Modeled	17,01	35,73	This audience consists of households in the top 15-20% of a model predicting an interest in Frozen. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.383	Godzilla	Interest Propensities	Movies	Media & Entertainment		Household	Modeled	18,13	38,08	This audience consists of households in the top 15-20% of a model predicting an interest in Godzilla. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.386	Harry Potter	Interest Propensities	Movies	Media & Entertainment		Household	Modeled	18,29	38,41	This audience consists of households in the top 15-20% of a model predicting an interest in Harry Potter. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.387	Heavy Pay-Per-View Movies Propensity	Interest Propensities	Movies	Media & Entertainment		Household	Modeled	10,83	22,74	This audience consists of households in the top 20% of a model predicting the likelihood that they have watched pay-per-view movies at least 4 times in the past 12 months. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.390	James Bond	Interest Propensities	Movies	Media & Entertainment		Household	Modeled	16,59	34,85	This audience consists of households in the top 15-20% of a model predicting an interest in James Bond. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.396	Marvel Comic Series	Interest Propensities	Movies	Media & Entertainment		Household	Modeled	17,27	36,27	This audience consists of households in the top 15-20% of a model predicting an interest in Marvel Comic Series. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.397	Mary Poppins (Mary Poppins Returns)	Interest Propensities	Movies	Media & Entertainment		Household	Modeled	16,52	34,70	This audience consists of households in the top 15-20% of a model predicting an interest in Mary Poppins (Mary Poppins Returns). The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.398	Pirates of the Caribbean	Interest Propensities	Movies	Media & Entertainment		Household	Modeled	14,94	31,38	This audience consists of households in the top 15-20% of a model predicting an interest in Pirates of the Caribbean. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.399	Pixar Movies	Interest Propensities	Movies	Media & Entertainment		Household	Modeled	44,24	92,91	This audience consists of households in the top 15-20% of a model predicting an interest in Pixar movies. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.403	The Avengers	Interest Propensities	Movies	Media & Entertainment		Household	Modeled	18,54	38,94	This audience consists of households in the top 15-20% of a model predicting an interest in The Avengers. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.404	The Eternals	Interest Propensities	Movies	Media & Entertainment		Household	Modeled	28,58	60,01	This audience consists of households in the top 15-20% of a model predicting an interest in The Eternals. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.405	The LEGO Movie	Interest Propensities	Movies	Media & Entertainment		Household	Modeled	16,72	35,11	This audience consists of households in the top 15-20% of a model predicting an interest in The LEGO Movie. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.406	Toy Story	Interest Propensities	Movies	Media & Entertainment		Household	Modeled	14,84	31,16	This audience consists of households in the top 15-20% of a model predicting an interest in Toy Story. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.408	Wonder Woman	Interest Propensities	Movies	Media & Entertainment		Household	Modeled	17,87	37,52	This audience consists of households in the top 15-20% of a model predicting an interest in Wonder Woman. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.409	Wreck it Ralph (Ralph Breaks the Internet)	Interest Propensities	Movies	Media & Entertainment		Household	Modeled	18,47	38,78	This audience consists of households in the top 15-20% of a model predicting an interest in Wreck it Ralph (Ralph Breaks the Internet). The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.410	X-Men	Interest Propensities	Movies	Media & Entertainment		Household	Modeled	17,65	37,06	This audience consists of households in the top 15-20% of a model predicting an interest in X-Men. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.414	Classic Rock	Interest Propensities	Music	Media & Entertainment		Household	Modeled	68,54	143,93	This audience consists of households in the top 15-20% of a model predicting an interest in Classic Rock. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.419	Classical Concert Attendee - Propensity	Interest Propensities	Music	Media & Entertainment		Household	Modeled	13,84	29,06	This audience consists of households in the top 20% of a model predicting they attend a classical music concert 2+ times per year. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.412	Country	Interest Propensities	Music	Media & Entertainment		Household	Modeled	63,75	133,88	This audience consists of households in the top 15-20% of a model predicting an interest in Country. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.420	Country Concert Attendee - Propensity	Interest Propensities	Music	Media & Entertainment		Household	Modeled	10,16	21,33	This audience consists of households in the top 20% of a model predicting they attend a country music concert 2+ times per year. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.415	Hip Hop and Rap	Interest Propensities	Music	Media & Entertainment		Household	Modeled	29,24	61,41	This audience consists of households in the top 15-20% of a model predicting an interest in Hip Hop and Rap. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.417	Metal	Interest Propensities	Music	Media & Entertainment		Household	Modeled	58,32	122,47	This audience consists of households in the top 15-20% of a model predicting an interest in Metal. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.416	Music	Interest Propensities	Music	Media & Entertainment		Household	Modeled	37,86	79,51	This audience consists of households in the top 15-20% of a model predicting an interest in Music. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.422	Premium Classical Concert Attendee - Propensity	Interest Propensities	Music	Media & Entertainment		Individual	Modeled	16,30	34,24	This audience consists of individuals in the top 20% of a model predicting they attend a classical music concert 2+ times per year. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.423	Premium Country Concert Attendee - Propensity	Interest Propensities	Music	Media & Entertainment		Individual	Modeled	11,85	24,89	This audience consists of individuals in the top 20% of a model predicting they attend a country music concert 2+ times per year. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.421	Rock Concert Attendee - Propensity	Interest Propensities	Music	Media & Entertainment		Household	Modeled	7,28	15,28	This audience consists of households in the top 20% of a model predicting they attend a rock music concert 2+ times per year. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.425	Arizona Cardinals	Interest Propensities	NFL	Sports		Household	Modeled	16,12	33,84	This audience consists of households in the top 15-20% of a model predicting an interest in Arizona Cardinals. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.426	Atlanta Falcons	Interest Propensities	NFL	Sports		Household	Modeled	16,04	33,69	This audience consists of households in the top 15-20% of a model predicting an interest in Atlanta Falcons. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.427	Baltimore Ravens	Interest Propensities	NFL	Sports		Household	Modeled	14,78	31,04	This audience consists of households in the top 15-20% of a model predicting an interest in Baltimore Ravens. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.428	Buffalo Bills	Interest Propensities	NFL	Sports		Household	Modeled	14,85	31,18	This audience consists of households in the top 15-20% of a model predicting an interest in Buffalo Bills. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.429	Carolina Panthers	Interest Propensities	NFL	Sports		Household	Modeled	15,18	31,89	This audience consists of households in the top 15-20% of a model predicting an interest in Carolina Panthers. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.430	Chicago Bears	Interest Propensities	NFL	Sports		Household	Modeled	14,06	29,52	This audience consists of households in the top 15-20% of a model predicting an interest in Chicago Bears. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.431	Cincinnati Bengals	Interest Propensities	NFL	Sports		Household	Modeled	14,93	31,35	This audience consists of households in the top 15-20% of a model predicting an interest in Cincinnati Bengals. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.432	Cleveland Browns	Interest Propensities	NFL	Sports		Household	Modeled	14,92	31,33	This audience consists of households in the top 15-20% of a model predicting an interest in Cleveland Browns. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.433	Dallas Cowboys	Interest Propensities	NFL	Sports		Household	Modeled	14,15	29,72	This audience consists of households in the top 15-20% of a model predicting an interest in Dallas Cowboys. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.434	Denver Broncos	Interest Propensities	NFL	Sports		Household	Modeled	16,76	35,19	This audience consists of households in the top 15-20% of a model predicting an interest in Denver Broncos. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.435	Detroit Lions	Interest Propensities	NFL	Sports		Household	Modeled	17,59	36,93	This audience consists of households in the top 15-20% of a model predicting an interest in Detroit Lions. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.436	Green Bay Packers	Interest Propensities	NFL	Sports		Household	Modeled	14,36	30,16	This audience consists of households in the top 15-20% of a model predicting an interest in Green Bay Packers. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.437	Houston Texans	Interest Propensities	NFL	Sports		Household	Modeled	14,65	30,77	This audience consists of households in the top 15-20% of a model predicting an interest in Houston Texans. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.438	Indianapolis Colts	Interest Propensities	NFL	Sports		Household	Modeled	15,99	33,58	This audience consists of households in the top 15-20% of a model predicting an interest in Indianapolis Colts. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.439	Jacksonville Jaguars	Interest Propensities	NFL	Sports		Household	Modeled	16,17	33,96	This audience consists of households in the top 15-20% of a model predicting an interest in Jacksonville Jaguars. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.440	Kansas City Chiefs	Interest Propensities	NFL	Sports		Household	Modeled	15,27	32,07	This audience consists of households in the top 15-20% of a model predicting an interest in Kansas City Chiefs. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.449	Las Vegas Raiders	Interest Propensities	NFL	Sports		Household	Modeled	14,77	31,02	This audience consists of households in the top 15-20% of a model predicting an interest in Oakland Raiders. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.441	Los Angeles Chargers	Interest Propensities	NFL	Sports		Household	Modeled	15,29	32,10	This audience consists of households in the top 15-20% of a model predicting an interest in Los Angeles Chargers. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.442	Los Angeles Rams	Interest Propensities	NFL	Sports		Household	Modeled	15,97	33,53	This audience consists of households in the top 15-20% of a model predicting an interest in Los Angeles Rams. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.443	Miami Dolphins	Interest Propensities	NFL	Sports		Household	Modeled	15,18	31,87	This audience consists of households in the top 15-20% of a model predicting an interest in Miami Dolphins. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.444	Minnesota Vikings	Interest Propensities	NFL	Sports		Household	Modeled	14,56	30,57	This audience consists of households in the top 15-20% of a model predicting an interest in Minnesota Vikings. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.445	New England Patriots	Interest Propensities	NFL	Sports		Household	Modeled	14,78	31,05	This audience consists of households in the top 15-20% of a model predicting an interest in New England Patriots. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.446	New Orleans Saints	Interest Propensities	NFL	Sports		Household	Modeled	14,73	30,93	This audience consists of households in the top 15-20% of a model predicting an interest in New Orleans Saints. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.447	New York Giants	Interest Propensities	NFL	Sports		Household	Modeled	15,73	33,03	This audience consists of households in the top 15-20% of a model predicting an interest in New York Giants. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.448	New York Jets	Interest Propensities	NFL	Sports		Household	Modeled	14,71	30,90	This audience consists of households in the top 15-20% of a model predicting an interest in New York Jets. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.450	Philadelphia Eagles	Interest Propensities	NFL	Sports		Household	Modeled	14,52	30,49	This audience consists of households in the top 15-20% of a model predicting an interest in Philadelphia Eagles. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.451	Pittsburgh Steelers	Interest Propensities	NFL	Sports		Household	Modeled	13,50	28,35	This audience consists of households in the top 15-20% of a model predicting an interest in Pittsburgh Steelers. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.457	Professional Football Fans - Propensity	Interest Propensities	NFL	Sports		Household	Modeled	6,49	13,63	This audience consists of households in the top 20% of a model predicting they have attended professional football games in the past year. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.452	San Francisco 49ers	Interest Propensities	NFL	Sports		Household	Modeled	14,30	30,02	This audience consists of households in the top 15-20% of a model predicting an interest in San Francisco 49ers. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.453	Seattle Seahawks	Interest Propensities	NFL	Sports		Household	Modeled	15,72	33,02	This audience consists of households in the top 15-20% of a model predicting an interest in Seatlle Seahawks. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.454	Tampa Bay Buccaneers	Interest Propensities	NFL	Sports		Household	Modeled	16,75	35,17	This audience consists of households in the top 15-20% of a model predicting an interest in Tampa Bay Buccaneers. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.455	Tennessee Titans	Interest Propensities	NFL	Sports		Household	Modeled	16,25	34,13	This audience consists of households in the top 15-20% of a model predicting an interest in Tennessee Titans. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.456	Washington Commanders	Interest Propensities	NFL	Sports		Household	Modeled	14,96	31,42	This audience consists of households in the top 15-20% of a model predicting an interest in Washington Redskins. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.461	Boston Bruins	Interest Propensities	NHL	Sports		Household	Modeled	15,74	33,06	This audience consists of households in the top 15-20% of a model predicting an interest in Boston Bruins. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.464	Carolina Hurricanes	Interest Propensities	NHL	Sports		Household	Modeled	16,90	35,50	This audience consists of households in the top 15-20% of a model predicting an interest in Carolina Hurricanes. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.471	Florida Panthers	Interest Propensities	NHL	Sports		Household	Modeled	16,67	35,00	This audience consists of households in the top 15-20% of a model predicting an interest in Florida Panthers. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.472	Los Angeles Kings	Interest Propensities	NHL	Sports		Household	Modeled	16,15	33,92	This audience consists of households in the top 15-20% of a model predicting an interest in Los Angeles Kings. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.473	Minnesota Wild	Interest Propensities	NHL	Sports		Household	Modeled	15,31	32,15	This audience consists of households in the top 15-20% of a model predicting an interest in Minnesota Wild. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.477	New York Islanders	Interest Propensities	NHL	Sports		Household	Modeled	16,00	33,60	This audience consists of households in the top 15-20% of a model predicting an interest in New York Islanders. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.478	New York Rangers	Interest Propensities	NHL	Sports		Household	Modeled	15,85	33,28	This audience consists of households in the top 15-20% of a model predicting an interest in New York Rangers. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.481	Philadelphia Flyers	Interest Propensities	NHL	Sports		Household	Modeled	15,18	31,88	This audience consists of households in the top 15-20% of a model predicting an interest in Philadelphia Flyers. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.484	St. Louis Blues	Interest Propensities	NHL	Sports		Household	Modeled	16,14	33,89	This audience consists of households in the top 15-20% of a model predicting an interest in St. Louis Blues. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.485	Tampa Bay Lightning	Interest Propensities	NHL	Sports		Household	Modeled	16,58	34,82	This audience consists of households in the top 15-20% of a model predicting an interest in Tampa Bay Lightning. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.488	Vegas Golden Knights	Interest Propensities	NHL	Sports		Household	Modeled	18,70	39,26	This audience consists of households in the top 15-20% of a model predicting an interest in Vegas Golden Knights. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.489	Washington Capitals	Interest Propensities	NHL	Sports		Household	Modeled	18,20	38,22	This audience consists of households in the top 15-20% of a model predicting an interest in Washington Capitals. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.492	AARP	Interest Propensities	Non-Profits	Non-Profit		Household	Modeled	16,10	33,82	This audience consists of households in the top 15-20% of a model predicting an interest in AARP. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.493	Alzheimer's Association	Interest Propensities	Non-Profits	Non-Profit		Household	Modeled	14,89	31,26	This audience consists of households in the top 15-20% of a model predicting an interest in Alzheimer's Association. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.494	American Diabetes Association	Interest Propensities	Non-Profits	Non-Profit		Household	Modeled	16,18	33,98	This audience consists of households in the top 15-20% of a model predicting an interest in American Diabetes Association. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.495	American Heart Association	Interest Propensities	Non-Profits	Non-Profit		Household	Modeled	16,28	34,19	This audience consists of households in the top 15-20% of a model predicting an interest in American Heart Association. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.496	American Red Cross	Interest Propensities	Non-Profits	Non-Profit		Household	Modeled	16,82	35,31	This audience consists of households in the top 15-20% of a model predicting an interest in American Red Cross. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.497	ASPCA	Interest Propensities	Non-Profits	Non-Profit		Household	Modeled	15,67	32,91	This audience consists of households in the top 15-20% of a model predicting an interest in ASPCA. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.498	Big Brothers/Big Sisters	Interest Propensities	Non-Profits	Non-Profit		Household	Modeled	18,93	39,76	This audience consists of households in the top 15-20% of a model predicting an interest in Big Brothers/Big Sisters. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.499	Boy Scouts of America	Interest Propensities	Non-Profits	Non-Profit		Household	Modeled	13,11	27,54	This audience consists of households in the top 15-20% of a model predicting an interest in Boy Scouts of America. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.500	Disabled American Veterans	Interest Propensities	Non-Profits	Non-Profit	Politics	Household	Modeled	16,23	34,09	This audience consists of households in the top 15-20% of a model predicting an interest in Disabled American Veterans. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.501	Doctors Without Borders	Interest Propensities	Non-Profits	Non-Profit		Household	Modeled	17,17	36,06	This audience consists of households in the top 15-20% of a model predicting an interest in Doctors Without Borders. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.514	Donor to PBS / NPR - Propensity	Interest Propensities	Non-Profits	Non-Profit		Household	Modeled	14,40	30,24	This audience consists of households in the top 20% of a model predicting they make donations to PBS/NPR with an annual overall contribution amount greater than $100. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.515	Environmental / Group Causes - Propensity	Interest Propensities	Non-Profits	Non-Profit		Household	Modeled	9,54	20,03	This audience consists of households in the top 20% of a model predicting they participate in environmental groups or causes. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.502	Feeding America	Interest Propensities	Non-Profits	Non-Profit		Household	Modeled	18,25	38,33	This audience consists of households in the top 15-20% of a model predicting an interest in Feeding America. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.503	Girl Scouts of America	Interest Propensities	Non-Profits	Non-Profit		Household	Modeled	15,55	32,65	This audience consists of households in the top 15-20% of a model predicting an interest in Girl Scouts of America. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.504	Habitat for Humanity	Interest Propensities	Non-Profits	Non-Profit		Household	Modeled	18,42	38,69	This audience consists of households in the top 15-20% of a model predicting an interest in Habitat for Humanity. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.505	Make-A-Wish Foundation	Interest Propensities	Non-Profits	Non-Profit		Household	Modeled	15,78	33,14	This audience consists of households in the top 15-20% of a model predicting an interest in Make-A-Wish Foundation. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.506	National Multiple Sclerosis Society	Interest Propensities	Non-Profits	Non-Profit		Household	Modeled	16,15	33,91	This audience consists of households in the top 15-20% of a model predicting an interest in National Multiple Sclerosis Society. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.516	Non-Religious Donor - Propensity	Interest Propensities	Non-Profits	Non-Profit		Household	Modeled	19,93	41,84	This audience consists of households in the top 20% of a model predicting they donate to non-religious organizations and causes. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.518	Premium Donor to PBS / NPR - Propensity	Interest Propensities	Non-Profits	Non-Profit		Individual	Modeled	17,15	36,02	This audience consists of individuals in the top 20% of a model predicting they make donations to PBS/NPR with an annual overall contribution amount greater than $100. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.519	Premium Environmental & Group Causes - Propensity	Interest Propensities	Non-Profits	Non-Profit		Individual	Modeled	11,12	23,35	This audience consists of individuals in the top 20% of a model predicting they participate in environmental groups or causes. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.520	Premium Non-Religious Donor - Propensity	Interest Propensities	Non-Profits	Non-Profit		Individual	Modeled	25,93	54,46	This audience consists of individuals in the top 20% of a model predicting they donate to non-religious organizations and causes. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.521	Premium Religious Donors - Propensity	Interest Propensities	Non-Profits	Non-Profit		Individual	Modeled	24,05	50,51	This audience consists of individuals in the top 20% of a model predicting they donate to religious organizations and causes with an annual contribution amount over $250. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.517	Religious Donors - Propensity	Interest Propensities	Non-Profits	Non-Profit		Household	Modeled	18,38	38,61	This audience consists of households in the top 20% of a model predicting they donate to religious organizations and causes with an annual contribution amount over $250. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.509	Save The Children	Interest Propensities	Non-Profits	Non-Profit		Household	Modeled	16,11	33,84	This audience consists of households in the top 15-20% of a model predicting an interest in Save The Children. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.510	Special Olympics	Interest Propensities	Non-Profits	Non-Profit		Household	Modeled	15,55	32,66	This audience consists of households in the top 15-20% of a model predicting an interest in Special Olympics. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.511	St. Jude Children's Research Hospital	Interest Propensities	Non-Profits	Non-Profit		Household	Modeled	15,54	32,64	This audience consists of households in the top 15-20% of a model predicting an interest in St. Jude Children's Research Hospital. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.512	Susan G. Komen	Interest Propensities	Non-Profits	Non-Profit		Household	Modeled	15,39	32,32	This audience consists of households in the top 15-20% of a model predicting an interest in Susan G. Komen. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.513	United Way	Interest Propensities	Non-Profits	Non-Profit		Household	Modeled	15,64	32,84	This audience consists of households in the top 15-20% of a model predicting an interest in United Way. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.523	BP	Interest Propensities	Oil & Gas	Oil & Gas		Household	Modeled	31,16	65,43	This audience consists of households in the top 15-20% of a model predicting an interest in BP. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.524	Chevron	Interest Propensities	Oil & Gas	Oil & Gas		Household	Modeled	30,56	64,17	This audience consists of households in the top 15-20% of a model predicting an interest in Chevron. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.525	Commonwealth Edison Co.	Interest Propensities	Oil & Gas	Oil & Gas		Household	Modeled	41,08	86,26	This audience consists of households in the top 15-20% of a model predicting an interest in Commonwealth Edison Co.. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.526	Consolidated Edison Co.	Interest Propensities	Oil & Gas	Oil & Gas		Household	Modeled	26,68	56,04	This audience consists of households in the top 15-20% of a model predicting an interest in Consolidated Edison Co.. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.528	Exxon	Interest Propensities	Oil & Gas	Oil & Gas		Household	Modeled	35,90	75,38	This audience consists of households in the top 15-20% of a model predicting an interest in Exxon. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.529	Florida Power & Light Co.	Interest Propensities	Oil & Gas	Oil & Gas		Household	Modeled	44,42	93,29	This audience consists of households in the top 15-20% of a model predicting an interest in Florida Power & Light Co.. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.530	Georgia Power Co.	Interest Propensities	Oil & Gas	Oil & Gas		Household	Modeled	46,74	98,15	This audience consists of households in the top 15-20% of a model predicting an interest in Georgia Power Co.. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.531	Pacific Gas & Electric Co (PG&E)	Interest Propensities	Oil & Gas	Oil & Gas		Household	Modeled	31,49	66,12	This audience consists of households in the top 15-20% of a model predicting an interest in Pacific Gas & Electric Co (PG&E). The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.533	Public Service Electric & Gas Co.	Interest Propensities	Oil & Gas	Oil & Gas		Household	Modeled	41,26	86,65	This audience consists of households in the top 15-20% of a model predicting an interest in Public Service Electric & Gas Co.. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.534	QuikTrip	Interest Propensities	Oil & Gas	Oil & Gas		Household	Modeled	55,40	116,34	This audience consists of households in the top 15-20% of a model predicting an interest in QuikTrip. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.535	Shell	Interest Propensities	Oil & Gas	Oil & Gas		Household	Modeled	34,32	72,08	This audience consists of households in the top 15-20% of a model predicting an interest in Shell. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.536	Southern California Edison Co.	Interest Propensities	Oil & Gas	Oil & Gas		Household	Modeled	34,67	72,80	This audience consists of households in the top 15-20% of a model predicting an interest in Southern California Edison Co.. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.537	Speedway	Interest Propensities	Oil & Gas	Oil & Gas		Household	Modeled	68,36	143,55	This audience consists of households in the top 15-20% of a model predicting an interest in Speedway. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.538	Sunoco	Interest Propensities	Oil & Gas	Oil & Gas		Household	Modeled	56,89	119,47	This audience consists of households in the top 15-20% of a model predicting an interest in Sunoco. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.539	Valero	Interest Propensities	Oil & Gas	Oil & Gas		Household	Modeled	30,13	63,27	This audience consists of households in the top 15-20% of a model predicting an interest in Valero. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.541	Boston Globe	Interest Propensities	Publications	Media & Entertainment		Household	Modeled	16,38	34,39	This audience consists of households in the top 15-20% of a model predicting an interest in Boston Globe. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.542	Chicago Tribune	Interest Propensities	Publications	Media & Entertainment		Household	Modeled	16,00	33,59	This audience consists of households in the top 15-20% of a model predicting an interest in Chicago Tribune. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.543	Los Angeles Times	Interest Propensities	Publications	Media & Entertainment		Household	Modeled	17,29	36,30	This audience consists of households in the top 15-20% of a model predicting an interest in Los Angeles Times. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.545	New York Post	Interest Propensities	Publications	Media & Entertainment		Household	Modeled	17,45	36,64	This audience consists of households in the top 15-20% of a model predicting an interest in New York Post. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.546	New York Times	Interest Propensities	Publications	Media & Entertainment		Household	Modeled	18,11	38,04	This audience consists of households in the top 15-20% of a model predicting an interest in New York Times. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.548	USA Today	Interest Propensities	Publications	Media & Entertainment		Household	Modeled	15,84	33,26	This audience consists of households in the top 15-20% of a model predicting an interest in USA Today. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.549	Wall Street Journal	Interest Propensities	Publications	Media & Entertainment		Household	Modeled	15,92	33,43	This audience consists of households in the top 15-20% of a model predicting an interest in Wall Street Journal. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.550	Washington Post	Interest Propensities	Publications	Media & Entertainment		Household	Modeled	18,01	37,82	This audience consists of households in the top 15-20% of a model predicting an interest in Washington Post. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.552	Arby's	Interest Propensities	QSR	QSR	Food & Beverage	Household	Modeled	16,43	34,49	This audience consists of households in the top 15-20% of a model predicting an interest in Arby's. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.553	Burger King	Interest Propensities	QSR	QSR	Food & Beverage	Household	Modeled	18,85	39,59	This audience consists of households in the top 15-20% of a model predicting an interest in Burger King. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.554	Chick-Fil-A	Interest Propensities	QSR	QSR	Food & Beverage	Household	Modeled	16,87	35,43	This audience consists of households in the top 15-20% of a model predicting an interest in Chick-Fil-A. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.555	Dairy Queen	Interest Propensities	QSR	QSR	Food & Beverage	Household	Modeled	16,81	35,31	This audience consists of households in the top 15-20% of a model predicting an interest in Dairy Queen. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.556	Fast Food - Propensity	Interest Propensities	QSR	QSR	Food & Beverage	Household	Modeled	8,82	18,52	This audience consists of individuals in the top 20% of a model predicting they visited fast food/drive through restaurant 9+ times and spent $200+ in the past 6 months. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.557	Hardee's	Interest Propensities	QSR	QSR	Food & Beverage	Household	Modeled	15,98	33,56	This audience consists of households in the top 15-20% of a model predicting an interest in Hardee's. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.558	Jack In the Box	Interest Propensities	QSR	QSR	Food & Beverage	Household	Modeled	15,62	32,81	This audience consists of households in the top 15-20% of a model predicting an interest in Jack In the Box. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.559	Kentucky Fried Chicken (KFC)	Interest Propensities	QSR	QSR	Food & Beverage	Household	Modeled	14,72	30,92	This audience consists of households in the top 15-20% of a model predicting an interest in Kentucky Fried Chicken (KFC). The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.560	McDonald's	Interest Propensities	QSR	QSR	Food & Beverage	Household	Modeled	16,30	34,23	This audience consists of households in the top 15-20% of a model predicting an interest in McDonald's. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.561	Popeye's	Interest Propensities	QSR	QSR	Food & Beverage	Household	Modeled	16,50	34,65	This audience consists of households in the top 15-20% of a model predicting an interest in Popeye's. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.562	Quiznos	Interest Propensities	QSR	QSR	Food & Beverage	Household	Modeled	16,76	35,19	This audience consists of households in the top 15-20% of a model predicting an interest in Quiznos. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.563	Sonic	Interest Propensities	QSR	QSR	Food & Beverage	Household	Modeled	16,31	34,25	This audience consists of households in the top 15-20% of a model predicting an interest in Sonic. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.564	Subway	Interest Propensities	QSR	QSR	Food & Beverage	Household	Modeled	16,74	35,16	This audience consists of households in the top 15-20% of a model predicting an interest in Subway. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.565	Taco Bell	Interest Propensities	QSR	QSR	Food & Beverage	Household	Modeled	17,22	36,16	This audience consists of households in the top 15-20% of a model predicting an interest in Taco Bell. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.566	Wendy's	Interest Propensities	QSR	QSR	Food & Beverage	Household	Modeled	15,41	32,36	This audience consists of households in the top 15-20% of a model predicting an interest in Wendy's. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.569	American Cuisine	Interest Propensities	Restaurants & Dining	Food & Beverage	QSR	Household	Modeled	70,29	147,61	This audience consists of households in the top 15-20% of a model predicting an interest in American Cuisine. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.229	Bistro MD	Interest Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	16,23	34,08	This audience consists of households in the top 15-20% of a model predicting an interest in Bistro MD. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.570	Chinese Cuisine	Interest Propensities	Restaurants & Dining	Food & Beverage	QSR	Household	Modeled	61,35	128,84	This audience consists of households in the top 15-20% of a model predicting an interest in Chinese Cuisine. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.568	Coffee	Interest Propensities	Restaurants & Dining	Food & Beverage	QSR	Household	Modeled	65,62	137,81	This audience consists of households in the top 15-20% of a model predicting an interest in Coffee. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.573	Family Restaurant Visitors - Propensity	Interest Propensities	Restaurants & Dining	Food & Beverage	QSR	Household	Modeled	10,89	22,87	This audience consists of households in the top 20% of a model predicting they have visited a family restaurant 8+ timesin the past month. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.572	Mexican Cuisine	Interest Propensities	Restaurants & Dining	Food & Beverage	QSR	Household	Modeled	50,09	105,19	This audience consists of households in the top 15-20% of a model predicting an interest in Mexican Cuisine. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.574	Premium Family Restaurant Visitors - Propensity	Interest Propensities	Restaurants & Dining	Food & Beverage	QSR	Individual	Modeled	12,85	26,99	This audience consists of individuals in the top 20% of a model predicting they visited a family restaurant 8+ times in the past 30 days. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
240.261	Nordic Track	Interest Propensities	Sporting Goods	Sports		Household	Modeled	15,82	33,23	This audience consists of households in the top 15-20% of a model predicting an interest in Nordic Track. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.576	Camping Propensity	Interest Propensities	Travel	Travel		Household	Modeled	11,02	23,14	This audience consists of households in the top 20% of a model predicting the likelihood they have gone on an overnight camping trip in the last 12 months. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.577	Cruise Travel - Propensity	Interest Propensities	Travel	Travel		Household	Modeled	16,68	35,02	This audience consists of households in the top 20% of a model predicting they traveled on 1+ cruise in the past 3 years. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.583	Economy Hotel Visitors - Propensity	Interest Propensities	Travel	Travel		Household	Modeled	10,98	23,06	This audience consists of households in the top 20% of a model predicting a stay in an economy hotel for personal/vacation travel. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.578	Foreign Travel For Vacation - Propensity	Interest Propensities	Travel	Travel		Household	Modeled	15,23	31,99	This audience consists of households in the top 20% of a model predicting they had foreign travel by plane for vacation 2+ times in the past 3 years. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.579	Frequent Business Traveler Propensity	Interest Propensities	Travel	Travel		Household	Modeled	10,66	22,39	This audience consists of households in the top 20% of a model predicting a member has taken 5+ business trips by plane in the past year . The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.580	Frequent Flyer Propensity	Interest Propensities	Travel	Travel		Household	Modeled	14,89	31,26	This audience consists of households in the top 20% of a model predicting a member has flown 5+ times in the past year . The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.581	High Mileage User Propensity	Interest Propensities	Travel	Travel		Household	Modeled	7,09	14,89	This audience consists of households in the top 20% of a model predicting the likelihood that at least one member of the household drives at least 30,000 miles in a year. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.582	Luxury Hotel Visitors - Propensity	Interest Propensities	Travel	Travel		Household	Modeled	13,50	28,34	This audience consists of households in the top 20% of a model predicting a luxury hotel stay for personal/vacation travel in the past 12 months. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.590	National Park Visitor Propensity	Interest Propensities	Travel	Travel		Household	Modeled	12,83	26,94	This audience consists of households in the top 20% of a model predicting they visited, or will visit a National Park on a vacation or trip. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.584	Online Travel Planners - Propensity	Interest Propensities	Travel	Travel		Household	Modeled	9,91	20,80	This audience consists of households in the top 20% of a model predicting personal or business travel plans made online. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.585	Premium Cruise Travel - Propensity	Interest Propensities	Travel	Travel		Individual	Modeled	21,50	45,15	This audience consists of individuals in the top 20% of a model predicting they traveled on 1+ cruises in the past 3 years. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.589	Premium Economy Hotel Visitors - Propensity	Interest Propensities	Travel	Travel		Individual	Modeled	12,84	26,97	This audience consists of individuals in the top 20% of a model predicting a stay in an economy hotel for personal/vacation travel. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.586	Premium Foreign Travel For Vacation - Propensity	Interest Propensities	Travel	Travel		Individual	Modeled	18,99	39,88	This audience consists of individuals in the top 20% of a model predicting they had foreign travel by plane for vacation 2+ times in the past 3 years. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.587	Premium Frequent Flyer Propensity	Interest Propensities	Travel	Travel		Individual	Modeled	18,58	39,01	This audience consists of individuals in the top 20% of a model predicting a member has flown 5+ times in the past year . The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.588	Premium Luxury Hotel Visitors - Propensity	Interest Propensities	Travel	Travel		Individual	Modeled	15,93	33,45	This audience consists of individuals in the top 20% of a model predicting a luxury hotel stay for personal/vacation travel in the past 12 months. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.591	Road Trip Propensity	Interest Propensities	Travel	Travel		Household	Modeled	12,98	27,26	This audience consists of households in the top 20% of a model predicting road trip(s) for personal travel/vacation and at least one member of the household driving 10,000+ miles a year in a personal/rental vehicle. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.592	Timeshare Owner Propensity	Interest Propensities	Travel	Travel		Household	Modeled	12,62	26,51	This audience consists of households in the top 20% of a model predicting ownership of a timeshare residence. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
240.428	Firestarter	Interest Propensities	TV	Media & Entertainment		Household	Modeled	50,33	105,70	This audience consists of households in the top 15-20% of a model predicting an interest in Firestarter. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.606	Heavy Pay-Per-View Sports Propensity	Interest Propensities	TV	Media & Entertainment		Household	Modeled	5,69	11,95	This audience consists of households in the top 20% of a model predicting the likelihood that they have watched pay-per-view sports at least 2 times in the past 12 months. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.607	Hispanic TV	Interest Propensities	TV	Media & Entertainment		Household	Modeled	16,20	34,01	This audience consists of households in the top 15-20% of a model predicting an interest in Hispanic TV. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.445	Pluto TV	Interest Propensities	TV	Media & Entertainment		Household	Modeled	16,20	34,01	This audience consists of households in the top 15-20% of a model predicting an interest in Pluto TV. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.615	Premium Subscription TV	Interest Propensities	TV	Media & Entertainment		Household	Modeled	42,49	89,24	This audience consists of households in the top 15-20% of a model predicting an interest in premium subscription tv. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.617	Satellite TV Propensity	Interest Propensities	TV	Media & Entertainment		Household	Modeled	8,49	17,84	This audience consists of households in the top 20% of a model predicting a subscription to satellite TV (DirecTV, Dish Network or Other). The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
240.437	Starz Originals	Interest Propensities	TV	Media & Entertainment		Household	Modeled	59,84	125,65	This audience consists of households in the top 15-20% of a model predicting an interest in Starz Originals. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.431	Tiger King	Interest Propensities	TV	Media & Entertainment		Household	Modeled	12,19	25,60	This audience consists of households in the top 15-20% of a model predicting an interest in Tiger King. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
637.041	2K Gaming	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	57,02	119,74	This audience consists of households in the top 15-20% of a model predicting an interest in 2K gaming. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.629	Activision	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	16,45	34,55	This audience consists of households in the top 15-20% of a model predicting an interest in Activision. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.630	Avid Gamers - Propensity	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	7,01	14,72	This audience consists of household in the top 20% of a model predicting they have spent $200/yr for games or hardware. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.631	Big Fish Games	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	16,33	34,29	This audience consists of households in the top 15-20% of a model predicting an interest in Big Fish Games. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.632	Candy Crush	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	15,04	31,58	This audience consists of households in the top 15-20% of a model predicting an interest in Candy Crush. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
637.042	Capcom	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	57,02	119,74	This audience consists of households in the top 15-20% of a model predicting an interest in Capcom. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.633	Dota 2	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	17,01	35,71	This audience consists of households in the top 15-20% of a model predicting an interest in Dota 2. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.634	ESL (formerly Electronic Sports League)	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	16,41	34,46	This audience consists of households in the top 15-20% of a model predicting an interest in ESL (formerly Electronic Sports League). The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.635	Fallout	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	16,12	33,84	This audience consists of households in the top 15-20% of a model predicting an interest in Fallout. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.636	Far Cry	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	16,30	34,23	This audience consists of households in the top 15-20% of a model predicting an interest in Far Cry. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.638	FIFA	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	15,33	32,20	This audience consists of households in the top 15-20% of a model predicting an interest in FIFA. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.639	Final Fantasy	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	15,80	33,17	This audience consists of households in the top 15-20% of a model predicting an interest in Final Fantasy. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.640	Fortnite	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	17,64	37,05	This audience consists of households in the top 15-20% of a model predicting an interest in Fortnite. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.641	Free to Play games	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	15,36	32,26	This audience consists of households in the top 15-20% of a model predicting an interest in Free to Play games. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.643	Hearthstone	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	17,80	37,37	This audience consists of households in the top 15-20% of a model predicting an interest in Hearthstone. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.644	League of Legends	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	16,92	35,54	This audience consists of households in the top 15-20% of a model predicting an interest in League of Legends. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.645	Legend of Zelda	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	17,49	36,72	This audience consists of households in the top 15-20% of a model predicting an interest in Legend of Zelda. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.646	Madden	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	19,28	40,49	This audience consists of households in the top 15-20% of a model predicting an interest in Madden. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
637.043	Meta Quest	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	57,02	119,74	This audience consists of households in the top 15-20% of a model predicting an interest in Meta Quest. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.648	Minecraft	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	16,82	35,32	This audience consists of households in the top 15-20% of a model predicting an interest in Minecraft. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.649	Mobile Games	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	15,67	32,90	This audience consists of households in the top 15-20% of a model predicting an interest in Mobile Games. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.650	NBA 2K	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	18,44	38,73	This audience consists of households in the top 15-20% of a model predicting an interest in NBA 2K. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.651	Ninja (Celebrity)	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	17,53	36,82	This audience consists of households in the top 15-20% of a model predicting an interest in Ninja (Celebrity). The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.652	Nintendo Switch	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	15,70	32,98	This audience consists of households in the top 15-20% of a model predicting an interest in Nintendo Switch. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.664	Online Gamers - Propensity	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	6,90	14,49	This audience consists of household in the top 20% of a model predicting online gaming activity. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.653	Overwatch	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	16,57	34,80	This audience consists of households in the top 15-20% of a model predicting an interest in Overwatch. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.654	Overwatch League	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	17,88	37,56	This audience consists of households in the top 15-20% of a model predicting an interest in Overwatch League. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.655	PC Gaming	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	15,38	32,29	This audience consists of households in the top 15-20% of a model predicting an interest in PC Gaming. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
637.044	Playstation 5	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	57,02	119,74	This audience consists of households in the top 15-20% of a model predicting an interest in Playstation 5. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.656	PS4	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	14,21	29,84	This audience consists of households in the top 15-20% of a model predicting an interest in PS4. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.657	Role Playing Games	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	15,89	33,37	This audience consists of households in the top 15-20% of a model predicting an interest in Role Playing Games. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.658	Steam	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	15,94	33,48	This audience consists of households in the top 15-20% of a model predicting an interest in Steam. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.659	Super Mario	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	15,77	33,12	This audience consists of households in the top 15-20% of a model predicting an interest in Super Mario. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.661	Twitch.com	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	17,01	35,72	This audience consists of households in the top 15-20% of a model predicting an interest in Twitch.com. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
637.045	Ubisoft	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	57,02	119,74	This audience consists of households in the top 15-20% of a model predicting an interest in Ubisoft. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.662	Video and Computer Games	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	43,06	90,44	This audience consists of households in the top 15-20% of a model predicting an interest in video and computer games. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.663	Xbox One	Interest Propensities	Video Games	Media & Entertainment		Household	Modeled	14,30	30,03	This audience consists of households in the top 15-20% of a model predicting an interest in Xbox One. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.684	Home Renovators	Movers & Homeowners	Home Renovation	Home		Household	Modeled	23,29	48,91	Household that have active home modeling projects. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.685	Pools	Movers & Homeowners	Home Renovation	Home		Household	Known	1,52	3,19	Household that have a swimming pool. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.669	Home Value $100-199k	Movers & Homeowners	Homeownership	Demographics	Financial Services	Household	Known	8,16	17,13	Households that live in a home valued at $100-199k. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.670	Home Value $200-299k	Movers & Homeowners	Homeownership	Demographics	Financial Services	Household	Known	7,44	15,62	Households that live in a home valued at $200-299k. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.671	Home Value $300-499k	Movers & Homeowners	Homeownership	Demographics	Financial Services	Household	Known	8,96	18,82	Households that live in a home valued at $300-499k. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.672	Home Value $500k+	Movers & Homeowners	Homeownership	Demographics	Financial Services	Household	Known	6,99	14,69	Households that live in a home valued at $500k+. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.668	Home Value Less than $100k	Movers & Homeowners	Homeownership	Demographics	Financial Services	Household	Known	4,21	8,83	Households that live in a home valued at less than $100k. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.667	Homeowner	Movers & Homeowners	Homeownership	Demographics	Financial Services	Household	Inferred	91,74	192,66	Households that own their home. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.673	Length of Residence 1 year or less	Movers & Homeowners	Homeownership	Demographics	Financial Services	Household	Known	3,00	6,29	Households have lived at the current residence 1 year or less. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.677	Length of Residence 10+ years	Movers & Homeowners	Homeownership	Demographics	Financial Services	Household	Known	55,38	116,30	Households have lived at the current residence for 10+ years. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.674	Length of Residence 1-3 years	Movers & Homeowners	Homeownership	Demographics	Financial Services	Household	Known	4,73	9,92	Households have lived at the current residence for 1-3 years. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.675	Length of Residence 3-5 years	Movers & Homeowners	Homeownership	Demographics	Financial Services	Household	Known	4,23	8,87	Households have lived at the current residence for 3-5 years. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.676	Length of Residence 6-9 years	Movers & Homeowners	Homeownership	Demographics	Financial Services	Household	Known	6,23	13,09	Households have lived at the current residence for 6-9 years. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.679	Premium Homeowner	Movers & Homeowners	Homeownership	Demographics	Financial Services	Individual	Inferred	151,98	319,15	Individuals that own their home. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.680	Premium Renter	Movers & Homeowners	Homeownership	Demographics	Financial Services	Individual	Modeled	29,01	60,92	Individuals that rent their current residence. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.678	Renter	Movers & Homeowners	Homeownership	Demographics	Financial Services	Household	Modeled	14,60	30,67	Households that rent their current residence. Demographics are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.691	New Movers - 3 Month	Movers & Homeowners	New Movers	Home		Household	Known	1,10	2,31	Households with self-reported change of addresses in the last 90 days.
13.689	New Movers - 30 Day	Movers & Homeowners	New Movers	Home		Household	Known	648,80	1,36	Households with self-reported change of addresses in the last 30 days.
13.692	New Movers - 6 Month	Movers & Homeowners	New Movers	Home		Household	Known	1,72	3,61	Households with self-reported change of addresses in the last 6 months.
13.690	New Movers - 60 Day	Movers & Homeowners	New Movers	Home		Household	Known	850,10	1,79	Households with self-reported change of addresses in the last 60 days.
13.693	New Movers - Local	Movers & Homeowners	New Movers	Home		Household	Known	1,38	2,90	Households who have recently moved less than 50 miles from their previous address.
13.694	New Movers - Long Distance	Movers & Homeowners	New Movers	Home		Household	Known	1,02	2,14	Households who have recently moved more than 50 miles from their previous address.
13.688	New Phone Connects	Movers & Homeowners	New Movers	Home		Household	Known	59,57	125,10	Households with have recently moved and had a new landline installed.
13.697	30 Day Pre-Movers	Movers & Homeowners	Pre-Movers	Home		Household	Known	255,58	536,72	The audience is built using households identified via real estate and newspaper listings within a 30 day period. These households are then further qualified with a match to Alliant DTC purchase transactions.
13.698	6 Month Pre-Movers	Movers & Homeowners	Pre-Movers	Home		Household	Known	1,08	2,27	The audience is built using households identified via real estate and newspaper listings within a 6 month period. These households are then further qualified with a match to Alliant DTC purchase transactions.
13.699	60 Day Pre-Movers	Movers & Homeowners	Pre-Movers	Home		Household	Known	508,80	1,07	The audience is built using households identified via real estate and newspaper listings within a 60 day period. These households are then further qualified with a match to Alliant DTC purchase transactions.
13.700	90 Day Pre-Movers	Movers & Homeowners	Pre-Movers	Home		Household	Known	711,56	1,49	The audience is built using households identified via real estate and newspaper listings within a 90 day period. These households are then further qualified with a match to Alliant DTC purchase transactions.
161.834	Pre-Mover Propensity	Movers & Homeowners	Pre-Movers	Home		Household	Modeled	15,79	33,16	This audience consists of households in the top 15-20% of a model predicting that they will soon be moving. The model is built using households identified via real-estate and newspaper listings within 0-3 days of posting as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.705	Affluent Democrat Seniors	Politics	Affluent Voters	Politics		Household	Known	2,49	5,24	Households that contain members who are 60+ years old, are registered Democrats and either make more than $85k a year or are in the top 25% of spenders in the Alliant cooperative. Demographics and political data are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.706	Affluent Early Boomer Democrats	Politics	Affluent Voters	Politics		Household	Known	878,77	1,85	Households that contain members who were born between 1946-1955, are registered Democrats and either make more than $85k a year or are in the top 25% of spenders in the Alliant cooperative. Demographics and political data are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.707	Affluent Early Boomer Independents	Politics	Affluent Voters	Politics		Household	Known	1,32	2,76	Households that contain members who were born between 1946-1955, are registered Independents and either make more than $85k a year or are in the top 25% of spenders in the Alliant cooperative. Demographics and political data are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.708	Affluent Early Boomer Republicans	Politics	Affluent Voters	Politics		Household	Known	1,02	2,14	Households that contain members who were born between 1946-1955, are registered Republicans and either make more than $85k a year or are in the top 25% of spenders in the Alliant cooperative. Demographics and political data are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.709	Affluent GenX Democrats	Politics	Affluent Voters	Politics		Household	Known	1,95	4,10	Households that contain members who were born between 1965-1983, are registered Democrats and either make more than $85k a year or are in the top 25% of spenders in the Alliant cooperative. Demographics and political data are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.710	Affluent GenX Independents	Politics	Affluent Voters	Politics		Household	Known	3,35	7,04	Households that contain members who were born between 1965-1983, are registered Independents and either make more than $85k a year or are in the top 25% of spenders in the Alliant cooperative. Demographics and political data are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.711	Affluent GenX Republicans	Politics	Affluent Voters	Politics		Household	Known	2,22	4,67	Households that contain members who were born between 1965-1983, are registered Republicans and either make more than $85k a year or are in the top 25% of spenders in the Alliant cooperative. Demographics and political data are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.712	Affluent Independent Seniors	Politics	Affluent Voters	Politics		Household	Known	3,97	8,34	Households that contain members who are 60+ years old, are registered Independents and either make more than $85k a year or are in the top 25% of spenders in the Alliant cooperative. Demographics and political data are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.713	Affluent Late Boomer Democrats	Politics	Affluent Voters	Politics		Household	Known	1,05	2,20	Households that contain members who were born between 1956-1964, are registered Democrats and either make more than $85k a year or are in the top 25% of spenders in the Alliant cooperative. Demographics and political data are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.714	Affluent Late Boomer Independents	Politics	Affluent Voters	Politics		Household	Known	1,77	3,71	Households that contain members who were born between 1956-1964, are registered Independents and either make more than $85k a year or are in the top 25% of spenders in the Alliant cooperative. Demographics and political data are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.715	Affluent Late Boomer Republicans	Politics	Affluent Voters	Politics		Household	Known	1,32	2,76	Households that contain members who were born between 1956-1964, are registered Republicans and either make more than $85k a year or are in the top 25% of spenders in the Alliant cooperative. Demographics and political data are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.716	Affluent Millennial Democrats	Politics	Affluent Voters	Politics		Household	Known	1,32	2,76	Households that contain members who were born between 1984-2002, are registered Democrats and either make more than $85k a year or are in the top 25% of spenders in the Alliant cooperative. Demographics and political data are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.717	Affluent Millennial Independents	Politics	Affluent Voters	Politics		Household	Known	2,31	4,84	Households that contain members who were born between 1984-2002, are registered Independents and either make more than $85k a year or are in the top 25% of spenders in the Alliant cooperative. Demographics and political data are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.718	Affluent Millennial Republicans	Politics	Affluent Voters	Politics		Household	Known	1,43	3,01	Households that contain members who were born between 1984-2002, are registered Republicans and either make more than $85k a year or are in the top 25% of spenders in the Alliant cooperative. Demographics and political data are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.719	Affluent Republican Seniors	Politics	Affluent Voters	Politics		Household	Known	3,03	6,37	Households that contain members who are 60+ years old, are registered Republicans and either make more than $85k a year or are in the top 25% of spenders in the Alliant cooperative. Demographics and political data are sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.756	Conservative Republican Propensity	Politics	Party Affiliations	Politics		Household	Modeled	3,91	8,21	This audience consists of households in the top 15-20% of a model predicting an interest in conservative Repbulicans. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.751	Democratic Party Affiliation	Politics	Party Affiliations	Politics		Household	Known	13,48	28,31	Households that contain members that are registered Democrats. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.760	Hispanic Democrat	Politics	Party Affiliations	Politics		Household	Known	1,20	2,52	Households that contain Hispanic members that are registered Democrats. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.761	Hispanic Independent	Politics	Party Affiliations	Politics		Household	Known	1,32	2,76	Households that contain Hispanic members that are registered Independents. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.762	Hispanic Republican	Politics	Party Affiliations	Politics		Household	Known	659,11	1,38	Households that contain Hispanic members that are registered Republicans. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.753	Independent Party Affiliation	Politics	Party Affiliations	Politics		Household	Known	20,68	43,42	Households that contain members that are registered Independents. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.766	Left Leaning Independents	Politics	Party Affiliations	Politics		Household	Inferred	1,13	2,38	Households that contain registered Independents who also express interest in Democrats via social or lifestyle data. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.767	Left Leaning Republicans	Politics	Party Affiliations	Politics		Household	Inferred	520,51	1,09	Households that contain registered Republicans who also express interest in Democrats via social or lifestyle data. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.768	Liberal Democrat Propensity	Politics	Party Affiliations	Politics		Household	Modeled	14,20	29,82	This audience consists of households in the top 20% of a model predicting an interest in liberal Democrats. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.769	Middle of the Road Democrat Propensity	Politics	Party Affiliations	Politics		Household	Modeled	6,15	12,92	This audience consists of households in the top 20% of a model predicting an interest in moderate Democrats. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.770	Middle of the Road Republican Propensity	Politics	Party Affiliations	Politics		Household	Modeled	7,76	16,30	This audience consists of households in the top 20% of a model predicting an interest in moderate Republicans. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.754	Politically Conservative - Propensity	Politics	Party Affiliations	Politics		Household	Modeled	27,96	58,71	This audience consists of households in the top 20% of a model predicting they consider themselves as very conservative. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.755	Politically Liberal - Propensity	Politics	Party Affiliations	Politics		Household	Modeled	18,94	39,78	This audience consists of households in the top 20% of a model predicting they consider themselves as liberal. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.778	Premium - Democratic Party Affiliation	Politics	Party Affiliations	Politics		Individual	Known	13,48	28,31	Individuals that contain members that are registered Democrats. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.780	Premium - Independent Party Affiliation	Politics	Party Affiliations	Politics		Individual	Known	20,68	43,42	Individuals that contain members that are registered Independents. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.779	Premium - Republican Party Affiliation	Politics	Party Affiliations	Politics		Individual	Known	12,01	25,22	Individuals that contain members that are registered Republicans. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.784	Premium Hispanic Democrat	Politics	Party Affiliations	Politics		Individual	Known	1,19	2,50	Individuals that are Hispanic members that are registered Democrats. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.790	Premium Left Leaning Independents	Politics	Party Affiliations	Politics		Individual	Inferred	1,22	2,56	Individuals that are registered Independents who also express interest in Democrats via social or lifestyle data. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.776	Premium Politically Conservative - Propensity	Politics	Party Affiliations	Politics		Individual	Modeled	55,34	116,21	This audience consists of individuals in the top 20% of a model predicting they consider themselves as very conservative. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
13.795	Premium Right Leaning Democrats	Politics	Party Affiliations	Politics		Individual	Known	1,43	3,01	Individuals that are registered Democrats who also express interest in Republicans via social or lifestyle data. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.796	Premium Right Leaning Independents	Politics	Party Affiliations	Politics		Individual	Known	2,81	5,91	Individuals that are registered Independents who also express interest in Republicans via social or lifestyle data. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.752	Republican Party Affiliation	Politics	Party Affiliations	Politics		Household	Known	12,01	25,22	Households that contain members that are registered Republicans. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.774	Right Leaning Democrats	Politics	Party Affiliations	Politics		Household	Inferred	1,24	2,61	Households that contain members that are registered Democrats who also express interest in Republicans via social or lifestyle data. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.775	Right Leaning Independents	Politics	Party Affiliations	Politics		Household	Inferred	2,05	4,30	Households that contain members that are registered Independents who also express interest in Republicans via social or lifestyle data. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.798	Environmental Donors - Democrat Voters	Politics	Political Donors	Politics		Household	Known	1,25	2,63	Households that contain members that are registered Democrats who have also made environmental donations. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.799	Environmental Donors - Independent Voters	Politics	Political Donors	Politics		Household	Known	1,99	4,17	Households that contain members that are registered Independents who have also made environmental donations. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.800	Environmental Donors - Republican Voters	Politics	Political Donors	Politics		Household	Known	1,23	2,59	Households that contain members that are registered Republicans who have also made environmental donations. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.801	Political Donors - Democrat Voters	Politics	Political Donors	Politics		Household	Known	184,95	388,40	Households that contain members that are registered Democrats who have also made political donations. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.802	Political Donors - Independent Voters	Politics	Political Donors	Politics		Household	Known	273,51	574,37	Households that contain members that are registered Independents who have also made political donations. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.803	Political Donors - Republican Voters	Politics	Political Donors	Politics		Household	Known	219,34	460,62	Households that contain members that are registered Republicans who have also made political donations. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.807	Premium Environmental Donors - Democrat Voters	Politics	Political Donors	Politics		Individual	Known	1,33	2,78	Individuals that are registered Democrats who have also made environmental donations. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.809	Premium Environmental Donors - Republican Voters	Politics	Political Donors	Politics		Individual	Known	1,40	2,94	Individuals that are registered Republicans who have also made environmental donations. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.810	Premium Political Donors - Democrat Voters	Politics	Political Donors	Politics		Individual	Known	202,55	425,35	Individuals that are registered Democrats who have also made political donations. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.811	Premium Political Donors - Independent Voters	Politics	Political Donors	Politics		Individual	Known	302,52	635,29	Individuals that are registered Independents who have also made political donations. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.812	Premium Political Donors - Republican Voters	Politics	Political Donors	Politics		Individual	Known	252,30	529,83	Individuals that are registered Republicans who have also made political donations. Political data is sourced from a national compiler and matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.817	Alexandria Ocasio-Cortez Voter Propensity	Politics	Political Leaders	Politics		Household	Modeled	18,74	39,35	This audience consists of households in the top 15-20% of a model predicting an interest in Alexandria Ocasio-Cortez. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.319	Asa Hutchinson	Politics	Political Leaders	Politics		Household	Modeled	51,22	107,57	This audience consists of households in the top 15-20% of a model predicting an interest in Asa Hutchinson. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.821	Beto O’Rourke Voter Propensity	Politics	Political Leaders	Politics		Household	Modeled	18,66	39,19	This audience consists of households in the top 15-20% of a model predicting an interest in Beto O’Rourke. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.315	Chris Christie	Politics	Political Leaders	Politics		Household	Modeled	48,35	101,54	This audience consists of households in the top 15-20% of a model predicting an interest in Chris Christie. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.443	Chuck Schumer	Politics	Political Leaders	Politics	Politics	Household	Modeled	43,54	91,44	This audience consists of households in the top 15-20% of a model predicting an interest in Chuck Schumer. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.448	Cori Bush	Politics	Political Leaders	Politics	Politics	Household	Modeled	34,48	72,40	This audience consists of households in the top 15-20% of a model predicting an interest in Cori Bush. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.324	Cornel West	Politics	Political Leaders	Politics		Household	Modeled	38,89	81,67	This audience consists of households in the top 15-20% of a model predicting an interest in Cornel West. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.440	Dan Crenshaw	Politics	Political Leaders	Politics	Politics	Household	Modeled	50,12	105,25	This audience consists of households in the top 15-20% of a model predicting an interest in Dan Crenshaw. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.835	Donald Trump Voter Propensity	Politics	Political Leaders	Politics		Household	Modeled	923,72	1,94	This audience consists of households in the top 15-20% of a model predicting an interest in Donald Trump. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.314	Doug Burgum	Politics	Political Leaders	Politics		Household	Modeled	39,61	83,17	This audience consists of households in the top 15-20% of a model predicting an interest in Doug Burgum. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.823	Elizabeth Warren Voter Propensity	Politics	Political Leaders	Politics		Household	Modeled	14,70	30,86	This audience consists of households in the top 15-20% of a model predicting an interest in Elizabeth Warren. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.321	Francis Suarez	Politics	Political Leaders	Politics		Household	Modeled	22,63	47,52	This audience consists of households in the top 15-20% of a model predicting an interest in Francis Suarez. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.452	Gavin Newsom	Politics	Political Leaders	Politics	Politics	Household	Modeled	27,40	57,54	This audience consists of households in the top 15-20% of a model predicting an interest in Gavin Newsom. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.839	Hillary Clinton Voter Propensity	Politics	Political Leaders	Politics		Household	Modeled	2,17	4,56	This audience consists of households in the top 15-20% of a model predicting an interest in Hillary Clinton. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.447	Ilhan Omar	Politics	Political Leaders	Politics	Politics	Household	Modeled	35,09	73,68	This audience consists of households in the top 15-20% of a model predicting an interest in Ilhan Omar. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.825	Joe Biden Voter Propensity	Politics	Political Leaders	Politics		Household	Modeled	35,86	75,31	This audience consists of households in the top 15-20% of a model predicting an interest in Joe Biden. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.829	Kamala Harris Voter Propensity	Politics	Political Leaders	Politics		Household	Modeled	16,50	34,66	This audience consists of households in the top 15-20% of a model predicting an interest in Kamala Harris. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.316	Larry Elder	Politics	Political Leaders	Politics		Household	Modeled	51,68	108,53	This audience consists of households in the top 15-20% of a model predicting an interest in Larry Elder. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.445	Liz Cheney	Politics	Political Leaders	Politics	Politics	Household	Modeled	50,85	106,78	This audience consists of households in the top 15-20% of a model predicting an interest in Liz Cheney. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.439	Marco Rubio	Politics	Political Leaders	Politics	Politics	Household	Modeled	36,00	75,59	This audience consists of households in the top 15-20% of a model predicting an interest in Marco Rubio. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.322	Marianne Williamson	Politics	Political Leaders	Politics		Household	Modeled	40,60	85,26	This audience consists of households in the top 15-20% of a model predicting an interest in Marianne Williamson. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.126	Mike Pence	Politics	Political Leaders	Politics		Household	Modeled	56,98	119,67	This audience consists of households in the top 15-20% of a model predicting an interest in Mike Pence. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.441	Mitch McConnell	Politics	Political Leaders	Politics	Politics	Household	Modeled	51,97	109,13	This audience consists of households in the top 15-20% of a model predicting an interest in Mitch McConnell. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.444	Mitt Romney	Politics	Political Leaders	Politics	Politics	Household	Modeled	39,55	83,05	This audience consists of households in the top 15-20% of a model predicting an interest in Mitt Romney. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.442	Nancy Pelosi	Politics	Political Leaders	Politics	Politics	Household	Modeled	47,49	99,74	This audience consists of households in the top 15-20% of a model predicting an interest in Nancy Pelosi. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.446	Nikki Haley	Politics	Political Leaders	Politics	Politics	Household	Modeled	49,63	104,22	This audience consists of households in the top 15-20% of a model predicting an interest in Nikki Haley. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.832	Pete Buttigieg Voter Propensity	Politics	Political Leaders	Politics		Household	Modeled	39,72	83,41	This audience consists of households in the top 15-20% of a model predicting an interest in Pete Buttigieg. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.323	Robert F. Kennedy Jr.	Politics	Political Leaders	Politics		Household	Modeled	44,14	92,70	This audience consists of households in the top 15-20% of a model predicting an interest in Robert F. Kennedy Jr. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.449	Ron DeSantis	Politics	Political Leaders	Politics	Politics	Household	Modeled	51,00	107,10	This audience consists of households in the top 15-20% of a model predicting an interest in Ron DeSantis. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.450	Stacey Abrams	Politics	Political Leaders	Politics	Politics	Household	Modeled	34,08	71,56	This audience consists of households in the top 15-20% of a model predicting an interest in Stacey Abrams. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
240.451	Tim Scott	Politics	Political Leaders	Politics	Politics	Household	Modeled	54,74	114,96	This audience consists of households in the top 15-20% of a model predicting an interest in Tim Scott. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.834	Tulsi Gabbard Voter Propensity	Politics	Political Leaders	Politics		Household	Modeled	15,33	32,20	This audience consists of households in the top 15-20% of a model predicting an interest in Tulsi Gabbard. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.320	Vivek Ramaswamy	Politics	Political Leaders	Politics		Household	Modeled	41,60	87,35	This audience consists of households in the top 15-20% of a model predicting an interest in Vivek Ramaswamy. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.318	Will Hurd	Politics	Political Leaders	Politics		Household	Modeled	32,00	67,21	This audience consists of households in the top 15-20% of a model predicting an interest in Will Hurd. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.734	Arts and Crafts Buyer Propensity	Product Propensities	Activities & Interests	Home		Household	Modeled	10,81	22,71	This audience consists of households in the top 10-20% of a model predicting a purchase of Arts And Crafts. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.733	Alcoholic Beverages Buyer Propensity	Product Propensities	Alcoholic Beverages	Food & Beverage		Household	Modeled	10,11	21,23	This audience consists of households in the top 10-20% of a model predicting a purchase of Alcoholic Beverages. The model is built using category-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.740	Children Clothing Buyer Propensity	Product Propensities	Apparel	Retail		Household	Modeled	9,62	20,20	This audience consists of households in the top 10-20% of a model predicting a purchase of Children Clothing. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.748	Fast Fashion Buyer Propensity	Product Propensities	Apparel	Retail		Household	Modeled	17,29	36,31	This audience consists of households in the top 10-20% of a model predicting a purchase of Fast Fashion. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.751	Footwear Buyer Propensity	Product Propensities	Apparel	Retail		Household	Modeled	9,13	19,17	This audience consists of households in the top 10-20% of a model predicting a purchase of Footwear. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.759	Mid Tier Department Stores Buyer Propensity	Product Propensities	Apparel	Retail		Household	Modeled	10,60	22,25	This audience consists of households in the top 10-20% of a model predicting a purchase of Mid Tier Department Stores. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.763	Off Price Department Stores Buyer Propensity	Product Propensities	Apparel	Retail		Household	Modeled	9,21	19,35	This audience consists of households in the top 10-20% of a model predicting a purchase of Off Price Department Stores. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.771	Plus Size Buyer Propensity	Product Propensities	Apparel	Retail		Household	Modeled	17,05	35,81	This audience consists of households in the top 10-20% of a model predicting a purchase of Plus Size. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.774	Specialty Apparel Buyer Propensity	Product Propensities	Apparel	Retail		Household	Modeled	13,81	29,00	This audience consists of households in the top 10-20% of a model predicting a purchase of Specialty Apparel. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.735	Auto Parts Buyer Propensity	Product Propensities	Auto	Auto		Household	Modeled	6,81	14,31	This audience consists of households in the top 10-20% of a model predicting a purchase of Auto Parts. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.842	Baby & Toddler Furniture	Product Propensities	Baby & Toddler	Home	Retail	Household	Modeled	24,22	50,87	This audience consists of households in the top 15-20% of a model predicting a purchase of baby & toddler furniture. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.843	Baby Bathing	Product Propensities	Baby & Toddler	Home	CPG	Household	Modeled	20,92	43,93	This audience consists of households in the top 15-20% of a model predicting a purchase of baby bathing products. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.844	Baby Gift Sets	Product Propensities	Baby & Toddler	Holiday	Retail	Household	Modeled	20,77	43,63	This audience consists of households in the top 15-20% of a model predicting a purchase of baby gift sets. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.845	Baby Safety	Product Propensities	Baby & Toddler	Home	Auto	Household	Modeled	20,72	43,51	This audience consists of households in the top 15-20% of a model predicting a purchase of baby safety products. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.846	Baby Toys	Product Propensities	Baby & Toddler	Home	Retail	Household	Modeled	22,20	46,62	This audience consists of households in the top 15-20% of a model predicting a purchase of baby toys. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.847	Baby Transport	Product Propensities	Baby & Toddler	Home	Auto	Household	Modeled	23,46	49,27	This audience consists of households in the top 15-20% of a model predicting a purchase of baby transport products. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.848	Baby Wipes	Product Propensities	Baby & Toddler	Home	CPG	Household	Modeled	20,84	43,76	This audience consists of households in the top 15-20% of a model predicting a purchase of baby wipes. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.849	Car Seat	Product Propensities	Baby & Toddler	Home	Auto	Household	Modeled	23,89	50,16	This audience consists of households in the top 15-20% of a model predicting a purchase of a car seat. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.850	Diapers	Product Propensities	Baby & Toddler	Home	CPG	Household	Modeled	23,20	48,71	This audience consists of households in the top 15-20% of a model predicting a purchase of diapers. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.852	Play Set	Product Propensities	Baby & Toddler	Home	Retail	Household	Modeled	19,59	41,14	This audience consists of households in the top 15-20% of a model predicting a purchase of play set. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.742	Discount Stores Buyer Propensity	Product Propensities	Big Box Retail	Retail		Household	Modeled	10,20	21,42	This audience consists of households in the top 10-20% of a model predicting a purchase of Discount Stores. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.779	Warehouse Clubs Buyer Propensity	Product Propensities	Big Box Retail	Retail		Household	Modeled	9,19	19,29	This audience consists of households in the top 10-20% of a model predicting a purchase of Warehouse Clubs. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.856	Costume Accessories	Product Propensities	Casual Wear	Retail		Household	Modeled	16,19	33,99	This audience consists of households in the top 15-20% of a model predicting a purchase of costume accessories. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.857	Denim	Product Propensities	Casual Wear	Retail		Household	Modeled	19,52	40,98	This audience consists of households in the top 15-20% of a model predicting a purchase of denim. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.858	Handbags, Wallets & Cases	Product Propensities	Casual Wear	Retail		Household	Modeled	28,12	59,06	This audience consists of households in the top 15-20% of a model predicting a purchase of handbags, wallets & cases. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.859	Jeans	Product Propensities	Casual Wear	Retail		Household	Modeled	17,86	37,50	This audience consists of households in the top 15-20% of a model predicting a purchase of jeans. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.860	Khaki	Product Propensities	Casual Wear	Retail		Household	Modeled	12,88	27,05	This audience consists of households in the top 15-20% of a model predicting a purchase of khakis. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.861	Pants	Product Propensities	Casual Wear	Retail		Household	Modeled	20,23	42,48	This audience consists of households in the top 15-20% of a model predicting a purchase of pants. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.862	Polo Shirt	Product Propensities	Casual Wear	Retail		Household	Modeled	13,32	27,98	This audience consists of households in the top 15-20% of a model predicting a purchase of polo shirts. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.865	Sweat Shirt	Product Propensities	Casual Wear	Retail		Household	Modeled	20,45	42,94	This audience consists of households in the top 15-20% of a model predicting a purchase of sweat shirts. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.866	Sweater	Product Propensities	Casual Wear	Retail		Household	Modeled	22,00	46,20	This audience consists of households in the top 15-20% of a model predicting a purchase of sweaters. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.868	Tank Top	Product Propensities	Casual Wear	Retail		Household	Modeled	21,96	46,11	This audience consists of households in the top 15-20% of a model predicting a purchase of tank tops. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.869	Tights	Product Propensities	Casual Wear	Retail		Household	Modeled	18,55	38,95	This audience consists of households in the top 15-20% of a model predicting a purchase of tights. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.867	T-Shirt	Product Propensities	Casual Wear	Retail		Household	Modeled	21,51	45,17	This audience consists of households in the top 15-20% of a model predicting a purchase of t-shirts. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.871	Camera & Optic Accessories	Product Propensities	Computer & Electronics	Tech		Household	Modeled	20,17	42,36	This audience consists of households in the top 15-20% of a model predicting a purchase of camera & optic accessories. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.872	Cameras	Product Propensities	Computer & Electronics	Tech		Household	Modeled	17,21	36,14	This audience consists of households in the top 15-20% of a model predicting a purchase of cameras. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.873	Computer Software	Product Propensities	Computer & Electronics	Tech		Household	Modeled	20,49	43,04	This audience consists of households in the top 15-20% of a model predicting a purchase of computer software. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.874	Smart Watch	Product Propensities	Computer & Electronics	Tech		Household	Modeled	20,65	43,36	This audience consists of households in the top 15-20% of a model predicting a purchase of a smart watch. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.875	Tablet Computer	Product Propensities	Computer & Electronics	Tech		Household	Modeled	19,16	40,23	This audience consists of households in the top 15-20% of a model predicting a purchase of a tablet computer. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.876	Video Game Consoles	Product Propensities	Computer & Electronics	Tech	Media & Entertainment	Household	Modeled	12,90	27,09	This audience consists of households in the top 15-20% of a model predicting a purchase of video game consoles. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.877	Video Game Software	Product Propensities	Computer & Electronics	Tech	Media & Entertainment	Household	Modeled	18,59	39,03	This audience consists of households in the top 15-20% of a model predicting a purchase of video game software. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.756	Internet Services Buyer Propensity	Product Propensities	Computer & Electronics	Tech		Household	Modeled	10,59	22,24	This audience consists of households in the top 10-20% of a model predicting a purchase of Internet Services. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.741	Convenience And Gas Buyer Propensity	Product Propensities	Convenience & Gas	Oil & Gas		Household	Modeled	16,68	35,02	This audience consists of households in the top 10-20% of a model predicting a purchase of Convenience And Gas. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.879	Blazer	Product Propensities	Dress Wear	Retail		Household	Modeled	20,17	42,36	This audience consists of households in the top 15-20% of a model predicting a purchase of a blazer. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.882	Dress	Product Propensities	Dress Wear	Retail		Household	Modeled	19,30	40,53	This audience consists of households in the top 15-20% of a model predicting a purchase of dresses. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.883	Dress Shirt	Product Propensities	Dress Wear	Retail		Household	Modeled	11,73	24,64	This audience consists of households in the top 15-20% of a model predicting a purchase of dress shirts. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.884	Shoes	Product Propensities	Dress Wear	Retail		Household	Modeled	23,28	48,89	This audience consists of households in the top 15-20% of a model predicting a purchase of shoes. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.743	Ebooks Buyer Propensity	Product Propensities	Education	Education		Household	Modeled	12,68	26,62	This audience consists of households in the top 10-20% of a model predicting a purchase of Ebooks. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.744	Education Resources Buyer Propensity	Product Propensities	Education	Education		Household	Modeled	12,54	26,33	This audience consists of households in the top 10-20% of a model predicting a purchase of Education Resources. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.745	Events And Attractions Buyer Propensity	Product Propensities	Events/Shows	Travel		Household	Modeled	13,05	27,40	This audience consists of households in the top 10-20% of a model predicting a purchase of Events And Attractions. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.777	Tax Preparation Buyer Propensity	Product Propensities	Financial	Financial Services		Household	Modeled	8,30	17,44	This audience consists of households in the top 10-20% of a model predicting a purchase of Tax Preparation. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.887	Jogger Pants	Product Propensities	Fitness Wear	Retail		Household	Modeled	16,76	35,21	This audience consists of households in the top 15-20% of a model predicting a purchase of jogger pants. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.747	Fast Casual Buyer Propensity	Product Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	14,85	31,19	This audience consists of households in the top 10-20% of a model predicting a purchase of Fast Casual. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.754	Home Beverages Buyer Propensity	Product Propensities	Food & Drugstore	Home		Household	Modeled	11,65	24,47	This audience consists of households in the top 10-20% of a model predicting a purchase of Home Beverages. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.775	Specialty Grocers Buyer Propensity	Product Propensities	Food & Drugstore	Food & Beverage		Household	Modeled	6,11	12,83	This audience consists of households in the top 10-20% of a model predicting a purchase of Specialty Grocers. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.736	Beauty Buyer Propensity	Product Propensities	Health & Beauty	Health & Beauty		Household	Modeled	15,21	31,94	This audience consists of households in the top 10-20% of a model predicting a purchase of Beauty. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.746	Eyewear Buyer Propensity	Product Propensities	Health & Beauty	Retail		Household	Modeled	13,56	28,48	This audience consists of households in the top 10-20% of a model predicting a purchase of Eyewear. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.749	Fitness Buyer Propensity	Product Propensities	Health & Beauty	Fitness		Household	Modeled	11,33	23,79	This audience consists of households in the top 10-20% of a model predicting a purchase of Fitness. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.767	Personal Care Buyer Propensity	Product Propensities	Health & Beauty	Health & Beauty		Household	Modeled	13,14	27,60	This audience consists of households in the top 10-20% of a model predicting a purchase of Personal Care. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.891	Probiotic	Product Propensities	Health Supplements	Health & Beauty	Fitness	Household	Modeled	17,88	37,55	This audience consists of households in the top 15-20% of a model predicting a purchase of probiotics. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.892	Supplement	Product Propensities	Health Supplements	Health & Beauty	Fitness	Household	Modeled	19,06	40,02	This audience consists of households in the top 15-20% of a model predicting a purchase of supplement products. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.770	Pharmacies Buyer Propensity	Product Propensities	Health Supplements	Health & Beauty		Household	Modeled	4,99	10,47	This audience consists of households in the top 10-20% of a model predicting a purchase of Pharmacies. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.895	Bathroom Accessories	Product Propensities	Home	Home		Household	Modeled	17,09	35,90	This audience consists of households in the top 15-20% of a model predicting a purchase of bathroom accessories. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.896	Business & Home Security	Product Propensities	Home	Home	Tech	Household	Modeled	16,47	34,59	This audience consists of households in the top 15-20% of a model predicting a purchase of business & home security. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.897	Coffeemaker	Product Propensities	Home	Home		Household	Modeled	22,61	47,49	This audience consists of households in the top 15-20% of a model predicting a purchase of a coffeemaker. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.898	Comforter Set	Product Propensities	Home	Home		Household	Modeled	21,91	46,00	This audience consists of households in the top 15-20% of a model predicting a purchase of comforter set. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.899	Curtain	Product Propensities	Home	Home		Household	Modeled	21,59	45,33	This audience consists of households in the top 15-20% of a model predicting a purchase of curtains. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.900	Exercise & Fitness	Product Propensities	Home	Home	Fitness	Household	Modeled	22,26	46,75	This audience consists of households in the top 15-20% of a model predicting a purchase of exercise & fitness products. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.902	Hardware Accessories	Product Propensities	Home	Home		Household	Modeled	20,67	43,40	This audience consists of households in the top 15-20% of a model predicting a purchase of hardware accessories. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.903	Household Appliances	Product Propensities	Home	Home		Household	Modeled	19,41	40,76	This audience consists of households in the top 15-20% of a model predicting a purchase of household appliances. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.904	Kitchen & Dining	Product Propensities	Home	Home		Household	Modeled	25,53	53,62	This audience consists of households in the top 15-20% of a model predicting a purchase of kitchen & dining products. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.905	Lighting	Product Propensities	Home	Home		Household	Modeled	21,13	44,37	This audience consists of households in the top 15-20% of a model predicting a purchase of lighting products. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.906	Linens & Bedding	Product Propensities	Home	Home		Household	Modeled	20,06	42,12	This audience consists of households in the top 15-20% of a model predicting a purchase of linens & bedding. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.907	Mattress Pad	Product Propensities	Home	Home		Household	Modeled	19,71	41,38	This audience consists of households in the top 15-20% of a model predicting a purchase of a mattress pad. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.909	Outdoor Furniture	Product Propensities	Home	Home		Household	Modeled	23,25	48,82	This audience consists of households in the top 15-20% of a model predicting a purchase of outdoor furniture. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.910	Outdoor Play Equipment	Product Propensities	Home	Home		Household	Modeled	26,45	55,54	This audience consists of households in the top 15-20% of a model predicting a purchase of outdoor play equipment. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.911	Outdoor Recreation	Product Propensities	Home	Home		Household	Modeled	21,21	44,54	This audience consists of households in the top 15-20% of a model predicting a purchase of outdoor recreation products. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.912	Plants	Product Propensities	Home	Home		Household	Modeled	15,72	33,01	This audience consists of households in the top 15-20% of a model predicting a purchase of plants. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.913	Plumbing	Product Propensities	Home	Home		Household	Modeled	20,81	43,71	This audience consists of households in the top 15-20% of a model predicting a purchase of plumbing products. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.914	Pool & Spa	Product Propensities	Home	Home		Household	Modeled	13,92	29,24	This audience consists of households in the top 15-20% of a model predicting a purchase of pool & spa products. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.915	Power & Electrical Supplies	Product Propensities	Home	Home		Household	Modeled	22,40	47,05	This audience consists of households in the top 15-20% of a model predicting a purchase of power & electrical supplies. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.916	Pressure Cooker	Product Propensities	Home	Home		Household	Modeled	20,96	44,03	This audience consists of households in the top 15-20% of a model predicting a purchase of a pressure cooker. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.917	Quilt Set	Product Propensities	Home	Home		Household	Modeled	21,59	45,34	This audience consists of households in the top 15-20% of a model predicting a purchase of quilt sets. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.918	Sheet Set	Product Propensities	Home	Home		Household	Modeled	23,26	48,86	This audience consists of households in the top 15-20% of a model predicting a purchase of sheet sets. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.919	Sofas	Product Propensities	Home	Home		Household	Modeled	24,43	51,30	This audience consists of households in the top 15-20% of a model predicting a purchase of sofas. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.920	Tools	Product Propensities	Home	Home		Household	Modeled	19,84	41,66	This audience consists of households in the top 15-20% of a model predicting a purchase of tools. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.921	Toys & Games	Product Propensities	Home	Home		Household	Modeled	23,04	48,38	This audience consists of households in the top 15-20% of a model predicting a purchase of toys & games. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.922	Vacuum Cleaner	Product Propensities	Home	Home		Household	Modeled	22,26	46,74	This audience consists of households in the top 15-20% of a model predicting a purchase of a vacuum cleaner. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.750	Florists Buyer Propensity	Product Propensities	Home	Holiday		Household	Modeled	10,65	22,37	This audience consists of households in the top 10-20% of a model predicting a purchase of Florists. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.757	Landscaping Buyer Propensity	Product Propensities	Home & Garden	Professional Services		Household	Modeled	6,67	14,00	This audience consists of households in the top 10-20% of a model predicting a purchase of Landscaping. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.753	General Merchandise Buyer Propensity	Product Propensities	Home & Household Goods	Retail		Household	Modeled	12,90	27,09	This audience consists of households in the top 10-20% of a model predicting a purchase of General Merchandise. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.755	Insurance Buyer Propensity	Product Propensities	Insurance	Financial Services		Household	Modeled	10,09	21,19	This audience consists of households in the top 10-20% of a model predicting a purchase of Insurance. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.925	Earring	Product Propensities	Jewelry	Retail		Household	Modeled	23,01	48,33	This audience consists of households in the top 15-20% of a model predicting a purchase of earrings. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.926	Jewelry	Product Propensities	Jewelry	Retail		Household	Modeled	26,02	54,64	This audience consists of households in the top 15-20% of a model predicting a purchase of jewelry. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.927	Jewelry Cleaning & Care	Product Propensities	Jewelry	Retail		Household	Modeled	14,84	31,16	This audience consists of households in the top 15-20% of a model predicting a purchase of jewelry cleaning & care products. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.928	Necklace	Product Propensities	Jewelry	Retail		Household	Modeled	23,51	49,38	This audience consists of households in the top 15-20% of a model predicting a purchase of necklaces. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.929	Ring	Product Propensities	Jewelry	Retail		Household	Modeled	22,98	48,27	This audience consists of households in the top 15-20% of a model predicting a purchase of rings. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.930	Watch	Product Propensities	Jewelry	Retail		Household	Modeled	18,04	37,87	This audience consists of households in the top 15-20% of a model predicting a purchase of watches. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.778	Toys Buyer Propensity	Product Propensities	Kids Products	Retail		Household	Modeled	12,29	25,81	This audience consists of households in the top 10-20% of a model predicting a purchase of Toys. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.758	Luxury Department Stores Buyer Propensity	Product Propensities	Luxury Brands	Retail		Household	Modeled	12,53	26,32	This audience consists of households in the top 10-20% of a model predicting a purchase of Luxury Department Stores. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.760	Movie Theaters Buyer Propensity	Product Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	11,14	23,40	This audience consists of households in the top 10-20% of a model predicting a purchase of Movie Theaters. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.761	Music Streaming Buyer Propensity	Product Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	8,20	17,22	This audience consists of households in the top 10-20% of a model predicting a purchase of Music Streaming. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.762	News Media Buyer Propensity	Product Propensities	Media & Entertainment	Media & Entertainment		Household	Modeled	6,17	12,95	This audience consists of households in the top 10-20% of a model predicting a purchase of News Media. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.738	Cable Providers Buyer Propensity	Product Propensities	MVPD	Telecom		Household	Modeled	8,80	18,47	This audience consists of households in the top 10-20% of a model predicting a purchase of Cable Providers. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.933	Hoodie	Product Propensities	Outerwear	Retail		Household	Modeled	15,32	32,17	This audience consists of households in the top 15-20% of a model predicting a purchase of hoodies. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.934	Jacket	Product Propensities	Outerwear	Retail		Household	Modeled	21,64	45,44	This audience consists of households in the top 15-20% of a model predicting a purchase of jackets. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.936	Body Wash	Product Propensities	Personal Care & Cosmetics	Health & Beauty	CPG	Household	Modeled	25,26	53,04	This audience consists of households in the top 15-20% of a model predicting a purchase of body wash. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.937	Cleanser	Product Propensities	Personal Care & Cosmetics	Health & Beauty	CPG	Household	Modeled	23,87	50,13	This audience consists of households in the top 15-20% of a model predicting a purchase of cleanser. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.938	Conditioner	Product Propensities	Personal Care & Cosmetics	Health & Beauty	CPG	Household	Modeled	24,01	50,42	This audience consists of households in the top 15-20% of a model predicting a purchase of conditioner. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.939	Eye Makeup	Product Propensities	Personal Care & Cosmetics	Health & Beauty	CPG	Household	Modeled	24,64	51,74	This audience consists of households in the top 15-20% of a model predicting a purchase of eye makeup. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.940	Foundation Makeup	Product Propensities	Personal Care & Cosmetics	Health & Beauty	CPG	Household	Modeled	26,20	55,02	This audience consists of households in the top 15-20% of a model predicting a purchase of foundation. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.941	Hair Color	Product Propensities	Personal Care & Cosmetics	Health & Beauty	CPG	Household	Modeled	22,33	46,89	This audience consists of households in the top 15-20% of a model predicting a purchase of hair color products. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.942	Lip Balm	Product Propensities	Personal Care & Cosmetics	Health & Beauty	CPG	Household	Modeled	22,79	47,85	This audience consists of households in the top 15-20% of a model predicting a purchase of lip balm. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.943	Lipstick	Product Propensities	Personal Care & Cosmetics	Health & Beauty	CPG	Household	Modeled	22,75	47,77	This audience consists of households in the top 15-20% of a model predicting a purchase of lipstick. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.944	Mascara	Product Propensities	Personal Care & Cosmetics	Health & Beauty	CPG	Household	Modeled	24,81	52,10	This audience consists of households in the top 15-20% of a model predicting a purchase of mascara. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.945	Mask	Product Propensities	Personal Care & Cosmetics	Health & Beauty	CPG	Household	Modeled	22,50	47,25	This audience consists of households in the top 15-20% of a model predicting a purchase of mask products. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.946	Moisturizer	Product Propensities	Personal Care & Cosmetics	Health & Beauty	CPG	Household	Modeled	25,20	52,91	This audience consists of households in the top 15-20% of a model predicting a purchase of moisturizer. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.947	Shampoo	Product Propensities	Personal Care & Cosmetics	Health & Beauty	CPG	Household	Modeled	24,39	51,21	This audience consists of households in the top 15-20% of a model predicting a purchase of shampoo. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.948	Skin Cream	Product Propensities	Personal Care & Cosmetics	Health & Beauty	CPG	Household	Modeled	24,84	52,16	This audience consists of households in the top 15-20% of a model predicting a purchase of skin cream. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.766	Payment Facilitators Buyer Propensity	Product Propensities	Personal Finance	Financial Services		Household	Modeled	12,88	27,04	This audience consists of households in the top 10-20% of a model predicting a purchase of Payment Facilitators. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.768	Personal Finance Buyer Propensity	Product Propensities	Personal Finance	Financial Services		Household	Modeled	11,62	24,40	This audience consists of households in the top 10-20% of a model predicting a purchase of Personal Finance. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.951	Cat Litter	Product Propensities	Pets	Pet	CPG	Household	Modeled	25,42	53,39	This audience consists of households in the top 15-20% of a model predicting a purchase of cat litter. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.952	Cat Toy	Product Propensities	Pets	Pet	CPG	Household	Modeled	23,82	50,02	This audience consists of households in the top 15-20% of a model predicting a purchase of cat toys. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.953	Dog Toy	Product Propensities	Pets	Pet	CPG	Household	Modeled	24,29	51,00	This audience consists of households in the top 15-20% of a model predicting a purchase of dog toys. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.954	Dog Treat	Product Propensities	Pets	Pet	CPG	Household	Modeled	24,70	51,87	This audience consists of households in the top 15-20% of a model predicting a purchase of dog treats. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.955	Dry Cat Food	Product Propensities	Pets	Pet	CPG	Household	Modeled	24,01	50,42	This audience consists of households in the top 15-20% of a model predicting a purchase of dry cat food. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.956	Dry Dog Food	Product Propensities	Pets	Pet	CPG	Household	Modeled	25,06	52,63	This audience consists of households in the top 15-20% of a model predicting a purchase of dry dog food. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.957	Wet Cat Food	Product Propensities	Pets	Pet	CPG	Household	Modeled	22,10	46,41	This audience consists of households in the top 15-20% of a model predicting a purchase of wet cat food. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.958	Wet Dog Food	Product Propensities	Pets	Pet	CPG	Household	Modeled	21,33	44,79	This audience consists of households in the top 15-20% of a model predicting a purchase of wet dog food. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.769	Pets Buyer Propensity	Product Propensities	Pets	Pet		Household	Modeled	13,74	28,85	This audience consists of households in the top 10-20% of a model predicting a purchase of Pets. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.737	Book Retailers Buyer Propensity	Product Propensities	Publications	Media & Entertainment		Household	Modeled	8,23	17,29	This audience consists of households in the top 10-20% of a model predicting a purchase of Book Retailers. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.739	Casual Dining Buyer Propensity	Product Propensities	Restaurants & Dining	Food & Beverage		Household	Modeled	16,33	34,30	This audience consists of households in the top 10-20% of a model predicting a purchase of Casual Dining. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.960	Nightgown	Product Propensities	Sleepwear	Retail		Household	Modeled	14,88	31,24	This audience consists of households in the top 15-20% of a model predicting a purchase of nightgowns. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.961	Pajamas	Product Propensities	Sleepwear	Retail		Household	Modeled	16,62	34,91	This audience consists of households in the top 15-20% of a model predicting a purchase of pajamas. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.962	Robe	Product Propensities	Sleepwear	Retail		Household	Modeled	19,26	40,46	This audience consists of households in the top 15-20% of a model predicting a purchase of robes. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.963	Sleepwear	Product Propensities	Sleepwear	Retail		Household	Modeled	14,51	30,46	This audience consists of households in the top 15-20% of a model predicting a purchase of sleepwear. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.764	Office Supplies Buyer Propensity	Product Propensities	Telecom & Service Providers	Telecom		Household	Modeled	7,82	16,43	This audience consists of households in the top 10-20% of a model predicting a purchase of Office Supplies. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.773	Shipping Buyer Propensity	Product Propensities	Telecom & Service Providers	Telecom		Household	Modeled	13,15	27,62	This audience consists of households in the top 10-20% of a model predicting a purchase of Shipping. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.965	Back Pack	Product Propensities	Travel	Retail		Household	Modeled	20,50	43,05	This audience consists of households in the top 15-20% of a model predicting a purchase of back packs. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.765	Parking Buyer Propensity	Product Propensities	Travel	Travel		Household	Modeled	17,19	36,10	This audience consists of households in the top 10-20% of a model predicting a purchase of Parking. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.772	Rideshare Buyer Propensity	Product Propensities	Travel	Travel		Household	Modeled	17,97	37,73	This audience consists of households in the top 10-20% of a model predicting a purchase of Rideshare. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.776	Storage Buyer Propensity	Product Propensities	Travel	Professional Services		Household	Modeled	14,94	31,37	This audience consists of households in the top 10-20% of a model predicting a purchase of Storage. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.974	Underwear	Product Propensities	Underwear	Retail		Household	Modeled	13,99	29,38	This audience consists of households in the top 15-20% of a model predicting a purchase of underwear. The model is built using product-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.752	Gaming Buyer Propensity	Product Propensities	Video Games	Media & Entertainment		Household	Modeled	21,11	44,33	This audience consists of households in the top 10-20% of a model predicting a purchase of Gaming. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
960.780	Accessories Product Buyer	Purchase Behaviors	Apparel	Retail		Household	Modeled	1,45	3,04	Households that have purchased (via digital and offline channels from DTC businesses) men?s and women?s styled accessories, such as jewelry, purses, handbags, hats, gloves and scarves.
960.781	Women's Apparel Product Buyer	Purchase Behaviors	Apparel	Retail		Household	Modeled	3,98	8,36	Households that have purchased (via digital and offline channels from DTC businesses) women?s apparel products, such as dresses, casual wear, and sleepwear.
960.782	Footwear Product Buyer	Purchase Behaviors	Apparel	Retail		Household	Modeled	3,75	7,88	Households that have purchased (via digital and offline channels from DTC businesses) footwear products, including men's and women's styles, such as running shoes, sandals, dress shoes, boots and socks.
960.785	Premium Accessories Product Buyer	Purchase Behaviors	Apparel	Retail		Individual	Modeled	0,00	0,00	Individuals in the Alliant Database that have purchased (via digital and offline channels from DTC businesses) men?s and women?s styled accessories, such as jewelry, purses, handbags, hats, gloves and scarves.
960.786	Premium Women's Apparel Product Buyer	Purchase Behaviors	Apparel	Retail		Individual	Modeled	0,00	0,00	Individuals in the Alliant Database that have purchased (via digital and offline channels from DTC businesses) women?s apparel products, such as dresses, casual wear, and sleepwear.
960.787	Premium Footwear Product Buyer	Purchase Behaviors	Apparel	Retail		Individual	Modeled	0,00	0,00	Individuals in the Alliant Database that have purchased (via digital and offline channels from DTC businesses) footwear products, including men's and women's styles, such as running shoes, sandals, dress shoes, boots and socks.
13.977	American Express Card Holder	Purchase Behaviors	Card Type	Financial Services		Household	Known	3,67	7,71	Households who are self-reported American Express cardholders, sourced from survey responses. Survey data is matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses). For individuals in this category use the Alliant Premium American Express Card Holder segment.
13.985	American Express Card Super Shoppers	Purchase Behaviors	Card Type	Financial Services		Household	Known	1,89	3,97	Households who are self-reported American Express cardholders, sourced from survey responses. Survey data is matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses), and identified as having made multiple purchases.
13.978	American Express Premium Card Holder	Purchase Behaviors	Card Type	Financial Services		Household	Known	645,10	1,35	Households who are self-reported American Express Premium cardholders, sourced from survey responses. Survey data is matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses). For individuals in this category use the Alliant Premium American Express Premium Card Holder segment.
13.979	Discover Card Holder	Purchase Behaviors	Card Type	Financial Services		Household	Known	3,16	6,64	Households who are self-reported Discover cardholders, sourced from survey responses. Survey data is matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses). For individuals in this category use the Alliant Premium Discover Card Holder segment.
13.986	Discover Card Super Shoppers	Purchase Behaviors	Card Type	Financial Services		Household	Known	2,44	5,13	Households who are self-reported Discover cardholders, sourced from survey responses. Survey data is matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses), and identified as having made multiple purchases.
13.980	Discover Premium Card Holder	Purchase Behaviors	Card Type	Financial Services		Household	Known	1,26	2,64	Households who are self-reported Discover Premium cardholders, sourced from survey responses. Survey data is matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses). For individuals in this category use the Alliant Premium Discover Premium Card Holder segment.
13.981	Mastercard Card Holder	Purchase Behaviors	Card Type	Financial Services		Household	Known	7,07	14,86	Households who are self-reported Mastercard cardholders, sourced from survey responses. Survey data is matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses). For individuals in this category use the Alliant Premium Mastercard Card Holder segment.
13.987	Mastercard Card Super Shoppers	Purchase Behaviors	Card Type	Financial Services		Household	Known	5,32	11,17	Households who are self-reported Mastercard cardholders, sourced from survey responses. Survey data is matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses), and identified as having made multiple purchases.
13.982	Mastercard Premium Card Holder	Purchase Behaviors	Card Type	Financial Services		Household	Known	2,59	5,45	Households who are self-reported Mastercard Premium cardholders, sourced from survey responses. Survey data is matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses). For individuals in this category use the Alliant Premium Mastercard Premium Card Holder segment.
13.996	Premium - Visa Card Holder	Purchase Behaviors	Card Type	Financial Services		Individual	Known	15,93	33,46	Individuals who are self-reported Visa cardholders, sourced from survey responses. Survey data is matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.997	Premium - Visa Premium Card Holder	Purchase Behaviors	Card Type	Financial Services		Individual	Known	5,10	10,71	Individuals who are self-reported Visa Gold cardholders, sourced from survey responses. Survey data is matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses).
13.983	Visa Card Holder	Purchase Behaviors	Card Type	Financial Services		Household	Known	15,93	33,46	Households who are self-reported Visa cardholders, sourced from survey responses. Survey data is matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses). For individuals in this category use the Alliant Premium VIsa Card Holder segment.
13.988	Visa Card Super Shoppers	Purchase Behaviors	Card Type	Financial Services		Household	Known	4,62	9,70	Households who are self-reported Visa cardholders, sourced from survey responses. Survey data is matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses), and identified as having made multiple purchases.
13.984	Visa Premium Card Holder	Purchase Behaviors	Card Type	Financial Services		Household	Known	5,10	10,71	Households who are self-reported Visa Gold cardholders, sourced from survey responses. Survey data is matched to the Alliant cooperative of known multichannel buyers (via digital and offline channels from DTC businesses). For individuals in this category use the Alliant Premium VIsa Gold Card Holder segment.
14.003	Direct Mail Orderers	Purchase Behaviors	Channel Preference	Retail		Household	Known	39,19	82,30	Households who purchase by direct mail as identified via Alliant transactions (via digital and offline channels from DTC businesses).
14.004	Internet or Email Orderers	Purchase Behaviors	Channel Preference	Retail		Household	Known	27,61	57,97	Households who respond to email and online offers as identified via Alliant transactions (via digital and offline channels from DTC businesses).
14.006	Premium Internet/Email Orderers	Purchase Behaviors	Channel Preference	Retail		Individual	Known	30,81	64,69	Individuals who respond to email and online offers as identified via Alliant transactions (via digital and offline channels from DTC businesses).
14.005	Telemarketing Orderers	Purchase Behaviors	Channel Preference	Retail		Household	Known	633,78	1,33	Households who respond to telemarketing offers as identified via Alliant transactions (via digital and offline channels from DTC businesses).
14.009	Active Hobbyists	Purchase Behaviors	Composites	Media & Entertainment		Household	Inferred	11,13	23,37	Households that have made frequent purchases (via digital and offline channels from DTC businesses) of Craft, Gardening and Hobby related products.
14.010	Active Hobbyists Online	Purchase Behaviors	Composites	Media & Entertainment		Household	Inferred	1,56	3,27	Households that have made frequent online purchases (via digital and offline channels from DTC businesses) of Craft, Gardening and Hobby related products.
14.032	Active Shopaholics	Purchase Behaviors	Composites	Retail		Household	Inferred	2,45	5,15	Households that are in the top 10% of orderers on Alliant's database and have made a purchase (via digital and offline channels from DTC businesses) in the last 30 days.
14.011	Affluent Consumers	Purchase Behaviors	Composites	Retail		Household	Inferred	31,05	65,21	Households that have purchased (via digital and offline channels from DTC businesses) and have an income greater than $85,000 or are in the top 25% of payers in the Alliant cooperative.
14.012	Affluent Men Shoppers	Purchase Behaviors	Composites	Retail		Household	Inferred	12,61	26,48	Households that contain males who have purchased (via digital and offline channels from DTC businesses) and have an income greater than $85,000 or are in the top 25% of payers in the Alliant cooperative.
14.013	Affluent Shopaholics	Purchase Behaviors	Composites	Retail		Household	Inferred	7,27	15,27	Households that are in the top 10% of orderers on Alliant's database, have a household income greater than $85,000 and are in the top 50% of payers.
14.014	Affluent Women Shoppers	Purchase Behaviors	Composites	Retail		Household	Inferred	19,62	41,20	Households that contain females who have purchased (via digital and offline channels from DTC businesses) and have an income greater than $85,000 or are in the top 25% of payers in the Alliant cooperative.
14.015	Cosmetic & Beauty Lovers	Purchase Behaviors	Composites	Health & Beauty		Household	Inferred	4,34	9,12	Households that have purchased (via digital and offline channels from DTC businesses) cosmetic, beauty and grooming products.
14.016	Crazy About Sports	Purchase Behaviors	Composites	Sports		Household	Inferred	4,42	9,29	Households that have purchased (via digital and offline channels from DTC businesses) multiple sports related products.
14.030	Digital Purchasing Parents	Purchase Behaviors	Composites	Retail		Household	Inferred	2,78	5,83	Households that have purchased (via digital channels from DTC businesses) parenting or children related products.
14.017	Focus on Politics Online	Purchase Behaviors	Composites	Politics		Household	Inferred	1,17	2,46	Households that have purchased (via digital channels from DTC businesses) products focused on politics / business online.
14.019	Home Gourmets Online	Purchase Behaviors	Composites	Food & Beverage	Home	Household	Inferred	30,32	63,67	Households that have purchased (via digital channels from DTC businesses) cooking and food related products.
14.020	Home Improvement Masters	Purchase Behaviors	Composites	Home		Household	Inferred	2,07	4,36	Households that contain males who have purchased (via digital channels from DTC businesses) home improvement related products such as woodworking or gardening.
14.021	Household Decision Makers	Purchase Behaviors	Composites	Home		Household	Inferred	41,13	86,37	Households in the Alliant database that purchase home products (via digital and offline channels from DTC businesses), meet their financial obligations and are in the top 50% payers in the Alliant cooperative.
14.022	King of the Wallet	Purchase Behaviors	Composites	Home		Household	Inferred	4,93	10,36	Households that have male interests, have an income of $150k+ and are in the top 20% of all spenders in the Alliant cooperative.
14.024	Literature & Music Lovers	Purchase Behaviors	Composites	Media & Entertainment		Household	Inferred	5,43	11,41	Households that have purchased (via digital and offline channels from DTC businesses) products related to personal time, including publications with opinion pieces on current events, entertainment and environmental issues.; plus reporting on the music scene, news and entertainers. Merchandise includes music/instructional how to play videos.
14.023	Loyal Super Spenders	Purchase Behaviors	Composites	Retail		Household	Inferred	7,57	15,90	Households that have purchased (via digital and offline channels from DTC businesses) multiple subscriptions and spent greater than $300.
14.025	Moms Who Buy Green	Purchase Behaviors	Composites	Retail		Household	Inferred	8,58	18,03	Households with moms who frequently buy family related products (via digital and offline channels from DTC businesses) and have an interest in environmental causes.
14.026	Moms Who Shop Like Crazy	Purchase Behaviors	Composites	Retail		Household	Inferred	10,22	21,47	Households with moms who frequently purchase (via digital and offline channels from DTC businesses)children's products from internet, direct mail and call centers as identified via Alliant transactions. Products include toys, puzzles, games, music and content for children.
14.027	News Hounds	Purchase Behaviors	Composites	Media & Entertainment		Household	Inferred	10,16	21,33	Households in the Alliant database that purchase (via digital and offline channels from DTC brands) products related to politics, current events and business. Including magazines and books covering domestic and foreign government issues, policies, decision makers, economics, law, finance, and career skills.
14.028	Personal Care Multibuyers	Purchase Behaviors	Composites	Retail		Household	Inferred	6,86	14,40	Households that have purchased (via digital and offline channels from DTC businesses) multiple products related to health and wellness, such as merchandise such as monitors, thermometers, nutraceuticals/supplements, and self-treatment aids; or magazines and books focused on specific illnesses, healthy cooking, special diets, fitness, weight loss, nutrition, and alternate cures / remedies.
14.053	Premium Active Shopaholics	Purchase Behaviors	Composites	Retail		Individual	Inferred	2,95	6,19	Individuals that are in the top 10% of orderers on Alliant's database and have made a purchase (via digital and offline channels from DTC businesses) in the last 30 days.
14.039	Premium Affluent Consumers	Purchase Behaviors	Composites	Retail		Individual	Inferred	34,84	73,17	Individuals that have purchased (via digital and offline channels from DTC businesses) and have an income greater than $85,000 or are in the top 25% of payers in the Alliant cooperative.
14.040	Premium Affluent Men Shoppers	Purchase Behaviors	Composites	Retail		Individual	Inferred	13,03	27,36	Males who have purchased (via digital and offline channels from DTC businesses) and have an income greater than $85,000 or are in the top 25% of payers in the Alliant cooperative.
14.041	Premium Affluent Shopaholics	Purchase Behaviors	Composites	Retail		Individual	Inferred	9,20	19,32	Individuals that are in the top 10% of orderers on Alliant's database, have a household income greater than $85,000 and are in the top 50% of payers.
14.042	Premium Affluent Women Shoppers	Purchase Behaviors	Composites	Retail		Individual	Inferred	20,67	43,41	Females who have purchased (via digital and offline channels from DTC businesses) and have an income greater than $85,000 or are in the top 25% of payers in the Alliant cooperative.
14.043	Premium Cosmetic & Beauty Lovers	Purchase Behaviors	Composites	Health & Beauty		Individual	Inferred	8,21	17,24	Individuals that have purchased (via digital and offline channels from DTC businesses) cosmetic, beauty and grooming products.
14.045	Premium Home Improvement Masters	Purchase Behaviors	Composites	Home		Individual	Inferred	2,15	4,51	Males who have purchased (via digital channels from DTC businesses) home improvement related products such as woodworking or gardening.
14.046	Premium Household Decision Makers	Purchase Behaviors	Composites	Home		Individual	Inferred	47,73	100,24	Individuals in the Alliant database that purchase home products (via digital and offline channels from DTC businesses), meet their financial obligations and are in the top 50% payers in the Alliant cooperative.
14.049	Premium Literature & Music Lovers	Purchase Behaviors	Composites	Media & Entertainment		Individual	Inferred	6,06	12,72	Individuals that have purchased (via digital and offline channels from DTC businesses) products related to personal time, including publications with opinion pieces on current events, entertainment and environmental issues; plus reporting on the music scene, news and entertainers. Merchandise includes music/instructional how to play videos.
14.050	Premium Moms Who Buy Green	Purchase Behaviors	Composites	Retail		Individual	Inferred	7,06	14,83	Moms who frequently buy family related products and have an interest in environmental causes.
14.051	Premium Moms Who Shop Like Crazy	Purchase Behaviors	Composites	Retail		Individual	Inferred	10,94	22,97	Moms who frequently buy children's products from internet, direct mail and call centers as identified via Alliant transactions. Products include toys, puzzles, games, music and content for children.
14.029	Purchasing Parents	Purchase Behaviors	Composites	Retail		Household	Inferred	11,30	23,73	Households that have purchased (via digital and offline channels from DTC businesses) parenting or children related products.
14.033	Sports & Fitness Buffs	Purchase Behaviors	Composites	Sports	Fitness	Household	Inferred	8,72	18,31	Households that have purchased (via digital and offline channels from DTC businesses) multiple products related sports, fitness and exercise and have bought in the past 90 days.
14.034	Sports & Fitness Buffs Online	Purchase Behaviors	Composites	Sports	Fitness	Household	Inferred	12,79	26,87	Households that have purchased (via digital channels from DTC businesses) multiple products related sports, fitness and exercise and have bought in the past 90 days.
14.038	Stylish Women	Purchase Behaviors	Composites	Retail		Household	Inferred	70,93	148,96	Households that contain females who have purchased (via digital and offline channels from DTC businesses) women's Fashion, Jewelry and Beauty related products and have an income greater than $100,000.
14.036	Women Born to Shop	Purchase Behaviors	Composites	Retail		Household	Inferred	16,92	35,54	Households that contain women that have purchased (via digital and offline channels from DTC businesses) multiple products related to jewelry, fashion, beauty, home and family.
960.784	Electronics Product Buyer	Purchase Behaviors	Electronics	Tech		Household	Modeled	1,47	3,08	Households that have purchased (via digital and offline channels from DTC businesses) electronics products, such as TVs, stereos, laptops, computers, turntables, tape recorders, radios and GPS devices.
960.789	Premium Electronics Product Buyer	Purchase Behaviors	Electronics	Tech		Individual	Modeled	0,00	0,00	Individuals in the Alliant Database that purchased (via digital and offline channels from DTC businesses) electronics products, such as TVs, stereos, laptops, computers, turntables, tape recorders, radios and GPS devices.
14.058	Arts & Crafts	Purchase Behaviors	Home & Garden	Media & Entertainment		Household	Known	5,02	10,54	Households that have purchased (via digital and offline channels from DTC businesses) home-based craft & hobby products, scrapbook supplies, stencils, sewing patterns, stitchery, quilting, keepsake albums & floral arranging products. Books, magazines and kits offering ideas, instructions and/or supplies to create your own crafts at home.
14.059	Cooking & Food Enthusiasts	Purchase Behaviors	Home & Garden	Food & Beverage	Home	Household	Known	38,88	81,64	Households that have purchased (via digital and offline channels from DTC businesses) cooking tools, gadgets, magazines & books. Merchandise includes baking & cookware and food preparation & storage equipment. Cookbooks and magazines offering recipes or advice on cooking techniques.
14.057	Home & Garden Interests	Purchase Behaviors	Home & Garden	Home		Household	Known	49,87	104,72	Households that have purchased (via digital and offline channels from DTC businesses) Home Décor, Lawn and Garden, Cooking or Arts and Crafts related products.
14.060	Home Decor	Purchase Behaviors	Home & Garden	Home		Household	Known	21,31	44,76	Households that have purchased (via digital and offline channels from DTC businesses) home decor products including calendars, posters, wall art, clocks, figurines, vases, candle holders, table linens & decorations, pillows, rugs, and bed & bath accessories. Books and magazines offering home decorating styles and tips.
14.061	House & Garden Enthusiasts	Purchase Behaviors	Home & Garden	Home		Household	Known	28,31	59,44	Households that have purchased products related to Home Decor, Lawn and Garden, Cooking or Arts and Crafts.
14.062	House & Garden Merchandise Buyers	Purchase Behaviors	Home & Garden	Home		Household	Known	28,70	60,28	Households that have purchased (via digital and offline channels from DTC businesses) home and garden related products.
14.063	Lawn & Garden Enthusiasts	Purchase Behaviors	Home & Garden	Home		Household	Known	17,52	36,78	Households that have purchased (via digital and offline channels from DTC businesses) gardening books, planners, plants, bulbs, seeds, yard and garden equipment and ornamentation. Instructional and hints/tips books and magazines focusing on techniques for flower, vegetable, ornamental, container and organic gardening, composting, and landscaping. Also includes gardening tools, equipment, plants, bulbs, pest repellers and garden ornaments such as wind chimes, statues, lights and decorative stones.
14.070	Premium Food	Purchase Behaviors	Home & Garden	Food & Beverage		Individual	Known	34,25	71,92	Individuals that have purchased (via digital and offline channels from DTC businesses) assorted candies, nuts, cookies, cheeses, spreads, and beverages, as well as books and magazines on specific foods and wine, including food preservation and food-specific cookbooks.
14.068	Premium Home & Garden Interests	Purchase Behaviors	Home & Garden	Demographics		Individual	Known	58,00	121,81	Individuals that have purchased (via digital and offline channels from DTC businesses) Home Décor, Lawn and Garden, Cooking or Arts and Crafts related products.
14.064	Premium Home Decor	Purchase Behaviors	Home & Garden	Home		Individual	Known	25,03	52,56	Individuals that have purchased (via digital and offline channels from DTC businesses) merchandise including calendars, posters, wall art, clocks, figurines, vases, candle holders, table linens & decorations, pillows, rugs, and bed & bath accessories. Books and magazines offering home decorating styles and tips.
14.065	Premium House & Garden Enthusiasts	Purchase Behaviors	Home & Garden	Home		Individual	Known	34,33	72,09	Individuals that have purchased (via digital and offline channels from DTC businesses) Home Décor, Lawn and Garden, Cooking or Arts and Crafts related products.
14.067	Premium Lawn & Garden Enthusiasts	Purchase Behaviors	Home & Garden	Home		Individual	Known	20,80	43,69	Individuals that have purchased (via digital and offline channels from DTC businesses) gardening books, planners, plants, bulbs, seeds, yard and garden equipment and ornamentation. Instructional and hints/tips books and magazines focusing on techniques for flower, vegetable, ornamental, container and organic gardening, composting, and landscaping. Also includes gardening tools, equipment, plants, bulbs, pest repellers and garden ornaments such as wind chimes, statues, lights and decorative stones.
960.783	Linens Product Buyer	Purchase Behaviors	Home & Household Goods	Home		Household	Modeled	1,65	3,47	Households that have purchased (via digital and offline channels from DTC businesses) linens products, such as towels, bedding and sheets.
960.788	Premium Linens Product Buyer	Purchase Behaviors	Home & Household Goods	Home		Individual	Modeled	0,00	0,00	Individuals in the Alliant Database that have purchased (via digital and offline channels from DTC businesses) linens products, such as towels, bedding and sheets.
14.072	Action-Adventure Enthusiasts	Purchase Behaviors	Lifestyle	Media & Entertainment		Household	Inferred	1,55	3,25	Households that have purchased (via digital and offline channels from DTC businesses) videos, books and magazines on extreme travel, sports, and exploration of both historical or fictional content. Merchandise includes apparel and equipment for such activities.
14.073	Book Fanatics	Purchase Behaviors	Lifestyle	Media & Entertainment		Household	Inferred	13,99	29,38	Households in the Alliant database who purchase books (via digital and offline channels from DTC businesses).
14.093	Cosmetics & Beauty	Purchase Behaviors	Lifestyle	Health & Beauty		Household	Known	8,75	18,38	Households in the Alliant database that purchased (via digital and offline channels from DTC businesses) beauty and grooming products. Merchandise includes lotions, make-up, fragrances, brushes, healthy skin and anti-aging aids, manicure sets, and nutraceuticals/supplements. Women's magazines with a focus on personal care & beauty, includes beauty tips and lifestyle hints to look your best.
14.090	Do-It-Yourself or Handyman	Purchase Behaviors	Lifestyle	Home		Household	Known	1,09	2,28	Households in the Alliant database who have purchased (via digital and offline channels from DTC businesses) merchandise including tools, craft kits designed specifically for children, or books and magazines devoted to crafts and home improvement projects offering tips, woodworking plans, and information on tools.
14.084	Fitness & Exercise	Purchase Behaviors	Lifestyle	Fitness	Health & Beauty	Household	Known	13,17	27,66	Households in the Alliant database who have purchased (via digital and offline channels from DTC businesses) fitness and exercise related products, including videos, magazines or books on running, bicycling, yoga, Pilates, personal training and workout routines. Also includes exercise equipment such as pedometers, massage rollers and air climber systems.
14.083	Health & Wellbeing	Purchase Behaviors	Lifestyle	Health & Beauty	Fitness	Household	Known	26,77	56,21	Households in the Alliant database who have purchased (via digital and offline channels from DTC businesses) products related to health and wellbeing.
14.085	Health, Wellness & Fitness	Purchase Behaviors	Lifestyle	Fitness	Health & Beauty	Household	Known	20,24	42,50	Households in the Alliant database who have purchased (via digital and offline channels from DTC businesses) products related to health, wellness and fitness, including monitors, thermometers, supplements, and self-treatment aids. Magazines and books focused on specific illnesses, healthy cooking, special diets, fitness, weight loss, nutrition, alternate cures / remedies.
14.074	History Buffs	Purchase Behaviors	Lifestyle	Media & Entertainment		Household	Inferred	5,52	11,59	Households that have purchased (via digital and offline channels from DTC businesses) videos and books about historic events, people, and places, both American and foreign; includes topics on Aviation, Natural History, Native American Indians, war and military heritage. Merchandise includes coins/collectibles, games, puzzles, toys, and related home accessories.
14.075	Hobbyists & Collectors	Purchase Behaviors	Lifestyle	Media & Entertainment		Household	Inferred	8,55	17,96	Households that have purchased (via digital and offline channels from DTC businesses) gaming, puzzles, collectibles, commemoratives and crafts. Merchandise includes craft kits; collectible coins, miniatures, and figurines; puzzles, photo/scrapbooking albums and musical instruments. Books and magazines on favorite leisure activities from collecting, crafting, genealogy, painting, and photography to bird watching, camping, horsemanship, cars, and sports; includes How To instructional books.
14.094	Jewelry & Accessories	Purchase Behaviors	Lifestyle	Health & Beauty		Household	Known	5,15	10,83	Households in the Alliant database that purchased (via digital and offline channels from DTC businesses) jewelry products including necklaces, bracelets, earrings, watches, rings, pins for either women, men or children.
14.076	Magazine Enthusiasts	Purchase Behaviors	Lifestyle	Media & Entertainment		Household	Inferred	46,16	96,94	Households in the Alliant database who subscribe (via digital and offline channels from DTC businesses) to general interest and specialty magazines.
14.077	Media & Entertainment Products	Purchase Behaviors	Lifestyle	Media & Entertainment		Household	Known	3,34	7,01	Households in the Alliant database who have purchased (via digital and offline channels from DTC businesses)in-home entertainment products.
14.089	Men's Interests	Purchase Behaviors	Lifestyle	Media & Entertainment		Household	Inferred	13,67	28,71	Households in the Alliant database that purchased (via digital and offline channels from DTC businesses) male related products and services, inclding culture, fashion, technology, entertainment and sports.
14.091	Men's Products	Purchase Behaviors	Lifestyle	Retail		Household	Known	14,15	29,72	Households in the Alliant database that purchased (via digital and offline channels from DTC businesses) male related products and services. Merchandise includes rings, watches, wallets, apparel, and personal care products. Books and magazines on Men's health, fitness training, weight loss diets, and sports.
14.078	Mystery & Horror Enthusiasts	Purchase Behaviors	Lifestyle	Media & Entertainment		Household	Inferred	537,52	1,13	Households in the Alliant database who have purchased (via digital and offline channels from DTC businesses) merchandise, media and entertainment related to mystery and horror.
14.079	Nature Lovers	Purchase Behaviors	Lifestyle	Media & Entertainment		Household	Inferred	5,73	12,03	Households in the Alliant database who have purchased (via digital and offline channels from DTC businesses) information and entertainment about nature. Merchandise includes weather instruments, compasses, maps, toys, and outdoor items. Books, magazines, and DVD's about plants, wildlife, prehistoric animals, weather, climate, biology, geology, physics, inventions and discoveries.
14.118	Premium Cosmetics & Beauty	Purchase Behaviors	Lifestyle	Health & Beauty		Individual	Known	9,82	20,61	Individuals in the Alliant database that purchased (via digital and offline channels from DTC businesses) beauty and grooming products. Merchandise includes lotions, make-up, fragrances, brushes, healthy skin and anti-aging aids, manicure sets, and Nutraceuticals/supplements. Includes Women's magazines with a focus on personal care & beauty, includes beauty tips and lifestyle hints to look your best.
14.098	Premium Entertainment & Pastimes	Purchase Behaviors	Lifestyle	Media & Entertainment		Individual	Known	60,67	127,41	Individuals in the Alliant database who purchase (via digital and offline channels from DTC businesses) entertainment, book and magazine products related to adventure, History, Hobby, Mystery, Science & Nature, Sports, and Fantasy/Science Fiction.
14.105	Premium Fitness & Exercise	Purchase Behaviors	Lifestyle	Fitness	Health & Beauty	Individual	Known	14,94	31,38	Individuals in the Alliant database who have purchased fitness and exercise related products, including videos, magazines or books on running, bicycling, yoga, Pilates, personal training and workout routines. Also includes exercise equipment such as pedometers, massage rollers and air climber systems.
14.104	Premium Health & Wellbeing	Purchase Behaviors	Lifestyle	Health & Beauty		Individual	Known	32,20	67,63	Individuals in the Alliant database who purchased (via digital and offline channels from DTC businesses) products related to health and wellbeing.
14.106	Premium Health, Wellness & Fitness	Purchase Behaviors	Lifestyle	Fitness	Health & Beauty	Individual	Known	24,19	50,79	Individuals in the Alliant database who have purchased products related to health, wellness and fitness, including monitors, thermometers, supplements, and self-treatment aids. Magazines and books focused on specific illnesses, healthy cooking, special diets, fitness, weight loss, nutrition, alternate cures / remedies.
14.101	Premium Magazine Enthusiasts	Purchase Behaviors	Lifestyle	Media & Entertainment		Individual	Inferred	22,46	47,16	Individuals in the Alliant database who subscribe (via digital and offline channels from DTC businesses) to general interest and specialty magazines.
14.115	Premium Men's Interests	Purchase Behaviors	Lifestyle	Media & Entertainment		Individual	Inferred	13,84	29,05	Individuals in the Alliant database that purchased (via digital and offline channels from DTC businesses) male related products and services.
14.107	Premium Self-Improvement	Purchase Behaviors	Lifestyle	Health & Beauty		Individual	Known	19,60	41,16	Individuals in the Alliant database who are interested in improving their homes, their relationships and their lives. Books, magazines and DVD's offering advice on a wide range of subjects from health to home improvement, cooking to computers, business and finance to personal relationships, gardening to parenting, and travel to weight loss; including planners and appointment journals.
14.103	Premium Sports Enthusiasts	Purchase Behaviors	Lifestyle	Sports		Individual	Inferred	10,33	21,69	Individuals in the Alliant database who purchase (via digital and offline channels from DTC businesses) media and products featuring personal, professional and school sports. Includes magazines, books and DVD's on spectator and participant sports; apparel, household goods and general merchandise with professional team logos; sports collectibles and memorabilia.
14.108	Premium Weight Loss	Purchase Behaviors	Lifestyle	Health & Beauty	Fitness	Individual	Known	10,30	21,64	Individuals in the Alliant database who have purchased (via digital and offline channels from DTC businesses) books, magazines and videos offering special diets, nutrition, recipes, exercise and health tips to control or modify eating habits and loss weight.
14.117	Premium Women's Interests	Purchase Behaviors	Lifestyle	Media & Entertainment		Individual	Inferred	29,82	62,61	Individuals in the Alliant database that purchased (via digital and offline channels from DTC businesses) products for women.
14.080	Puzzles & Games	Purchase Behaviors	Lifestyle	Media & Entertainment		Household	Known	7,28	15,30	Households in the Alliant database who have purchased (via digital and offline channels from DTC businesses) puzzle and game related products including merchandise and books designed for children and adults; brainteasers, trivia and memory games; jigsaw, crossword and Sudoku puzzles; video games.
14.081	Sci-Fi Enthusiasts	Purchase Behaviors	Lifestyle	Media & Entertainment		Household	Known	798,19	1,68	Households in the Alliant database who have purchased (via digital and offline channels from DTC businesses) products and services featuring science fiction. Magazines, books and DVD's for science-fiction enthusiasts on futuristic topics, outer space, UFO's, and psychics.
14.087	Self-Improvement	Purchase Behaviors	Lifestyle	Health & Beauty		Household	Known	16,18	33,98	Households in the Alliant database who have purchased (via digital and offline channels from DTC businesses) products for improving their homes, their relationships and their lives. Books, magazines and DVD's offering advice on a wide range of subjects from health to home improvement, cooking to computers, business and finance to personal relationships, gardening to parenting, and travel to weight loss; include planners and appointment journals.
14.096	Sewing & Needle Crafts	Purchase Behaviors	Lifestyle	Media & Entertainment		Household	Known	1,67	3,50	Households in the Alliant database that purchased (via digital and offline channels from DTC businesses) how-to information and supplies for arts and crafts such as sewing, knitting, stitchery and scrapbooking products. Instructional books on sewing, knitting, crocheting, quilting, embroidery, cross-stitch, and needlepoint. Merchandise includes craft kits, materials and equipment for these various areas.
14.082	Sports Enthusiasts	Purchase Behaviors	Lifestyle	Sports		Household	Known	3,99	8,38	Households in the Alliant database who purchase (via digital and offline channels from DTC businesses) media and products featuring personal, professional and school sports. Includes magazines, books and DVD's on spectator and participant sports; apparel, household goods and general merchandise with professional team logos; sports collectibles and memorabilia.
14.088	Weight Loss	Purchase Behaviors	Lifestyle	Health & Beauty	Fitness	Household	Known	9,11	19,12	Households in the Alliant database who have purchased (via digital and offline channels from DTC businesses) books, magazines and videos offering special diets, nutrition, recipes, exercise and health tips to control or modify eating habits and loss weight.
14.092	Women's Interests	Purchase Behaviors	Lifestyle	Retail		Household	Inferred	27,09	56,89	Households in the Alliant database that purchased (via digital and offline channels from DTC businesses) female related products and services, including women's magazines and products, including jewelry, sewing & needle craft hobbies, cosmetics/personal beauty and romantic lifestyle products.
14.097	Women's Products	Purchase Behaviors	Lifestyle	Retail		Household	Known	19,89	41,78	Households in the Alliant database that purchased (via digital and offline channels from DTC businesses) media, products and services featuring: fashion, entertainment, culture, weddings, beauty tips, gossip and the latest trends. Merchandise includes cosmetics, apparel, and jewelry. Magazines and books devoted to various women's topics including fashion, beauty, health, fitness, weight loss, relationships and parenting. Also includes fictional novels with a focus on female characters.
14.123	Book Multibuyers	Purchase Behaviors	Multibuyers	Media & Entertainment		Household	Known	5,36	11,25	Households in the Alliant database who have purchased (via digital and offline channels from DTC businesses) multiple books.
14.124	Club/Continuity Buyers	Purchase Behaviors	Multibuyers	Retail		Household	Known	28,46	59,78	Households in the Alliant database who have purchased (via digital and offline channels from DTC businesses) club or subscription products.
14.125	Continuity Multibuyers	Purchase Behaviors	Multibuyers	Retail		Household	Known	11,02	23,15	Households in the Alliant database who have purchased mutliple club or subscription products.
14.129	DTC Buyers	Purchase Behaviors	Multibuyers	Retail		Household	Known	45,99	96,57	Households in the Alliant database who have purchased products or merchandise directly from brands.
14.130	DTC Multibuyers	Purchase Behaviors	Multibuyers	Retail		Household	Known	28,53	59,91	Households in the Alliant database who have purchased multiple products or merchandise directly from brands.
14.126	Entertainment & Pastime Multibuyers	Purchase Behaviors	Multibuyers	Media & Entertainment		Household	Known	36,69	77,06	Households that purchased 2 or more entertainment/pastimes products across the Alliant database (via digital and offline channels from DTC businesses).
14.127	Internet Multibuyers	Purchase Behaviors	Multibuyers	Media & Entertainment		Household	Known	16,98	35,66	Households that purchased multiple products across the Alliant database (via digital channels from DTC businesses).
14.128	Magazine Multibuyers	Purchase Behaviors	Multibuyers	Media & Entertainment		Household	Known	13,79	28,96	Households that purchased multiple magazine products across the Alliant database (via digital and offline channels from DTC businesses).
14.122	Multibuyer Behaviors	Purchase Behaviors	Multibuyers	Retail		Household	Known	50,52	106,08	Households in the Alliant database who have purchased (via digital and offline channels from DTC businesses) multiple products or merchandise across brands/product lines or channels.
14.131	Multibuyers	Purchase Behaviors	Multibuyers	Media & Entertainment		Household	Known	27,47	57,69	Households in the Alliant database who have purchased multiple products or merchandise across brands/product lines or channels.
14.132	Paid with Cash or Check	Purchase Behaviors	Multibuyers	Financial Services		Household	Known	26,89	56,46	Households in the Alliant database who prefer to pay for their digital and offline purchases using cash or checks.
14.133	Paid with Credit Card	Purchase Behaviors	Multibuyers	Financial Services		Household	Known	58,39	122,61	Households in the Alliant database that regularly use their credit and debit cards for digital and offline purchases.
14.142	Premium DTC Buyers	Purchase Behaviors	Multibuyers	Retail		Individual	Known	52,57	110,39	Individuals in the Alliant database who have purchased (via digital and offline channels from DTC businesses) products or merchandise directly from brands.
14.143	Premium DTC Multibuyers	Purchase Behaviors	Multibuyers	Retail		Individual	Known	32,15	67,52	Individuals in the Alliant database who have purchased (via digital and offline channels from DTC businesses) multiple products or merchandise directly from brands.
14.138	Premium Entertainment & Pastimes Multibuyers	Purchase Behaviors	Multibuyers	Media & Entertainment		Individual	Known	45,13	94,77	Individuals that purchased 2 or more entertainment/pastimes products across the Alliant database (via digital and offline channels from DTC businesses).
14.139	Premium Internet Multibuyers	Purchase Behaviors	Multibuyers	Retail		Individual	Known	26,10	54,80	Individuals that purchased multiple products across the Alliant database (via digital channels from DTC businesses).
14.140	Premium Magazine Multibuyers	Purchase Behaviors	Multibuyers	Media & Entertainment		Individual	Known	16,49	34,62	Individuals that purchased multiple magazine products across the Alliant database (via digital and offline channels from DTC businesses).
14.144	Premium Multibuyer Behaviors	Purchase Behaviors	Multibuyers	Retail		Individual	Known	59,96	125,92	Individuals in the Alliant database who have purchased multiple products or merchandise across brands/product lines or channels.
14.146	Premium Shopaholics	Purchase Behaviors	Multibuyers	Retail		Individual	Inferred	32,24	67,70	Individuals in the top 10% of product orders on Alliant's database
14.134	Shopaholics	Purchase Behaviors	Multibuyers	Retail		Household	Inferred	24,29	51,02	Households that are in the top 10% of orderers on Alliant's database.
14.217	African American Product Buyers	Purchase Behaviors	Product Buyers	Retail		Household	Known	602,45	1,27	Households in the Alliant database who purchase (via digital and offline channels from DTC businesses) books and magazines for or by African Americans offering perspective on the African American community; topics cover news, history, fashion, lifestyle, parenting, cultural insight, and health issues.
14.218	Apparel Product Buyers	Purchase Behaviors	Product Buyers	Retail		Household	Known	13,39	28,13	Households in the Alliant database who purchase (via digital and offline channels from DTC businesses) apparel, including clothing for men, women, and children. Ranges from outerwear to sleepwear; shirts, dresses, sweaters, shoes, socks/hosiery, undergarments and accessories such as belts, gloves, scarves, hats, wallets, and purses.
14.219	As Seen On TV Buyers	Purchase Behaviors	Product Buyers	Retail		Household	Known	861,07	1,81	Households that have purchased (via digital and offline channels from DTC businesses) products offered via TV infomercials and home shopping networks across Alliant database.
14.220	Big Spenders	Purchase Behaviors	Product Buyers	Retail		Household	Known	10,17	21,36	Households that are in the top 20% of spend in the Alliant database.
14.221	Box / Product Subscribers	Purchase Behaviors	Product Buyers	Retail		Household	Known	25,41	53,36	Households in the Alliant database who subscribe (via digital and offline channels from DTC businesses) to merchandise.
14.222	Business Product Buyer	Purchase Behaviors	Product Buyers	Retail		Household	Known	7,42	15,58	Households in the Alliant database who purchase (via digital and offline channels from DTC businesses) business related products, including books and magazines with a focus on business acumen, economics, law, finance, and career skills, or desk accessories.
14.223	Children's Products	Purchase Behaviors	Product Buyers	Home		Household	Known	9,43	19,80	Households in the Alliant database who purchase (via digital and offline channels from DTC businesses) toys, books, DVD's & music for children. Books, magazines and videos geared to early learning skills, reading development, science/nature, fictional characters/fantasy themes, and Biblical stories; activity and sticker books; arts and crafts; children's music; toys, games, and puzzles.
14.224	CPG - Household Goods	Purchase Behaviors	Product Buyers	CPG		Household	Known	7,66	16,08	Households in the Alliant database who purchase (via digital and offline channels from DTC businesses)CPG or household goods.
14.226	Credit Challenged	Purchase Behaviors	Product Buyers	Financial Services		Household	Known	2,69	5,65	Households who struggle to meet payment obligations as identified via Alliant transactions.
14.225	Credit Seekers	Purchase Behaviors	Product Buyers	Financial Services		Household	Known	187,22	393,16	Households who struggle to meet payment obligations as identified via Alliant transactions.
14.215	Direct Marketing Purchasers	Purchase Behaviors	Product Buyers	Retail		Household	Known	81,73	171,63	Households in the Alliant database who have purchased (via digital and offline channels from DTC businesses) products or merchandise directly from brands.
14.216	Direct Marketing Responders	Purchase Behaviors	Product Buyers	Retail		Household	Known	84,53	177,51	Households in the Alliant database who have purchased (via digital and offline channels from DTC businesses) multiple products or merchandise directly from brands.
14.227	Education/Teacher	Purchase Behaviors	Product Buyers	Education		Household	Known	10,52	22,08	Households in the Alliant database who purchase (via digital and offline channels from DTC businesses) instructional books, magazines, kits and maps that promote early learning skills including reading, language, science, history and music . Also includes teacher handbooks and guides.
14.228	Emerging Consumers	Purchase Behaviors	Product Buyers	Financial Services		Household	Known	10,56	22,17	Households in the Alliant database that do not always live up to their financial obligations and are in the bottom 50% payers in the Alliant cooperative.
14.229	Entertainment & Pastimes Product Buyers	Purchase Behaviors	Product Buyers	Media & Entertainment		Household	Known	50,89	106,87	Households in the Alliant database who purchase (via digital and offline channels from DTC businesses) entertainment, book and magazine products related to adventure, History, Hobby, Mystery, Science & Nature, Sports, and Fantasy/Science Fiction.
14.230	Financial Interests	Purchase Behaviors	Product Buyers	Financial Services		Household	Known	3,74	7,86	Households in the Alliant database who purchase (via digital and offline channels from DTC businesses) financial products and services. Magazines, newsletters, and books offering advice on personal finance, investments, retirement, consumer spending, career and business success.
14.231	Financially in Charge	Purchase Behaviors	Product Buyers	Financial Services		Household	Inferred	82,34	172,92	Households in the Alliant database that meet their financial obligations and are in the top 50% payers in the Alliant cooperative.
14.232	Holiday Products	Purchase Behaviors	Product Buyers	Holiday		Household	Known	2,69	5,65	Households in the Alliant database who have purchased (via digital and offline channels from DTC businesses) family and entertainment products related to holidays and celebrations. Holiday-themed stories, decorations, cards, crafts, music, foods, cookbooks, and entertaining tips.
14.233	MultiChannel Super Spenders	Purchase Behaviors	Product Buyers	Retail		Household	Known	9,31	19,54	Households in the Alliant database who purchase (via digital and offline channels from DTC businesses) across channels including digital, direct mail and telemarketing.
14.235	Online Service Subscribers	Purchase Behaviors	Product Buyers	Media & Entertainment		Household	Known	14,34	30,11	Households in the Alliant database that are digital subscribers to services, memberships, and clubs.
14.236	Pet Lovers	Purchase Behaviors	Product Buyers	Pet		Household	Known	4,15	8,72	Households in the Alliant database who have purchased (via digital and offline channels from DTC businesses) pet products and gear. DVD's, books and magazines regarding household pets, wildlife, zoo animals and prehistoric animals, as well as toys and pet products.
14.246	Premium Big Spenders	Purchase Behaviors	Product Buyers	Retail		Individual	Inferred	17,96	37,71	Individuals that are in the top 20% of spend in the Alliant database.
14.243	Premium Children's Products	Purchase Behaviors	Product Buyers	Retail		Individual	Known	11,03	23,17	Individuals in the Alliant database who purchase toys, books, DVD's & music for children. Books, magazines and videos geared to early learning skills, reading development, science/nature, fictional characters/fantasy themes, and Biblical stories; activity and sticker books; arts and crafts; children's music; toys, games, and puzzles.
14.244	Premium Credit Seekers	Purchase Behaviors	Product Buyers	Financial Services		Individual	Inferred	3,41	7,15	Individuals who struggle to meet payment obligations as identified via Alliant transactions.
14.240	Premium Direct Marketing Responders	Purchase Behaviors	Product Buyers	Retail		Individual	Known	99,30	208,54	Individuals in the Alliant database who buy direct from brands-- online, in the mail and over the phone across the Alliant database.
14.245	Premium Financial Interests	Purchase Behaviors	Product Buyers	Financial Services		Individual	Inferred	4,24	8,91	Individuals in the Alliant database who purchase (via digital and offline channels from DTC businesses) financial products and services. Magazines, newsletters, and books offering advice on personal finance, investments, retirement, consumer spending, career and business success.
14.248	Premium Spiritual/Religious Product Buyers	Purchase Behaviors	Product Buyers	Retail		Individual	Known	4,75	9,97	Individuals in the Alliant database who have purchased (via digital and offline channels from DTC businesses) products related to alternative lifestyles and organized religion. Bibles and Bible stories; daily devotional journals and prayers; spiritually inspired stories, philosophy and self-help advice; Christian and Gospel music; religious jewelry & accessories like crosses and angels.
14.237	Spanish Language Product Buyers	Purchase Behaviors	Product Buyers	Retail		Household	Known	109,41	229,76	Households in the Alliant database who have purchased (via digital and offline channels from DTC businesses) books, magazines and other media in Spanish. Spanish language books, magazines, and videos on health issues, cooking, women's fashion, entertainment, and children's stories; includes dictionaries and instructional language guides to speak Spanish.
14.238	Spiritual and Religious Product Buyers	Purchase Behaviors	Product Buyers	Retail		Household	Known	3,99	8,37	Households in the Alliant database who have purchased (via digital and offline channels from DTC businesses) products related to alternative lifestyles and organized religion. Bibles and Bible stories; daily devotional journals and prayers; spiritually inspired stories, philosophy and self-help advice; Christian and Gospel music; religious jewelry & accessories like crosses and angels.
14.239	Vacation and Travel Products	Purchase Behaviors	Product Buyers	Travel		Household	Known	6,18	12,97	Households in the Alliant database who have purchased (via digital and offline channels from DTC businesses) books, magazines, and guides focused on foreign or domestic travel, National parks, cruise, train, or budget travel. Merchandise includes maps; luggage; travel wallets, clocks, apparel and hats; and travel related video.
14.250	30 Day Purchasers	Purchase Behaviors	Recency	Retail		Household	Known	3,60	7,57	Households that have made a purchase (via digital and offline channels from DTC businesses) in the last 0-30 days across the Alliant database.
14.251	60 Day Purchasers	Purchase Behaviors	Recency	Retail		Household	Known	5,82	12,23	Households that have made a purchase (via digital and offline channels from DTC businesses) in the last 60 days across the Alliant database.
14.252	90 Day Purchasers	Purchase Behaviors	Recency	Retail		Household	Known	7,37	15,47	Households that have made a purchase (via digital and offline channels from DTC businesses) in the last 90 days across the Alliant database.
14.253	Premium 30 Day Purchasers	Purchase Behaviors	Recency	Retail		Individual	Known	4,24	8,90	Individuals that have made a purchase (via digital and offline channels from DTC businesses) in the last 0-30 days across the Alliant database.
14.254	Premium 60 Day Purchasers	Purchase Behaviors	Recency	Retail		Individual	Known	6,86	14,41	Individuals that have made a purchase (via digital and offline channels from DTC businesses) in the last 60 days across the Alliant database.
14.255	Premium 90 Day Purchasers	Purchase Behaviors	Recency	Retail		Individual	Known	8,70	18,27	Individuals that have made a purchase (via digital and offline channels from DTC businesses) in the last 90 days across the Alliant database.
637.023	Apple TV Loyalists	TV Subscribers	Behaviors	Media & Entertainment		Household	Modeled	22,94	48,17	Households that Alliant has identified to be loyal in their continued subscription to Apple TV. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.972	Cord Cutters Propensity	TV Subscribers	Behaviors	Media & Entertainment		Household	Modeled	20,27	42,56	This audience consists of households in the top 15-20% of a model predicting cord cutter propensity. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.973	Cord Extenders Propensity	TV Subscribers	Behaviors	Media & Entertainment		Household	Modeled	19,22	40,36	This audience consists of households in the top 15-20% of a model predicting cord extender propensity. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
637.024	Dish Loyalists	TV Subscribers	Behaviors	Media & Entertainment		Household	Modeled	20,99	44,09	Households that Alliant has identified to be loyal in their continued subscription to Dish. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
637.026	FuboTV Loyalists	TV Subscribers	Behaviors	Media & Entertainment		Household	Modeled	21,16	44,44	Households that Alliant has identified to be loyal in their continued subscription to FuboTV. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
637.021	Hulu Loyalists	TV Subscribers	Behaviors	Media & Entertainment		Household	Modeled	21,61	45,38	Households that Alliant has identified to be loyal in their continued subscription to Hulu. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
637.019	Netflix Loyalists	TV Subscribers	Behaviors	Media & Entertainment		Household	Modeled	23,25	48,83	Households that Alliant has identified to be loyal in their continued subscription to Netflix. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
637.022	Paramount Loyalists	TV Subscribers	Behaviors	Media & Entertainment		Household	Modeled	21,77	45,71	Households that Alliant has identified to be loyal in their continued subscription to Paramount. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
637.028	Philo Loyalists	TV Subscribers	Behaviors	Media & Entertainment		Household	Modeled	21,17	44,46	Households that Alliant has identified to be loyal in their continued subscription to Philo. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
637.025	Redbox Loyalists	TV Subscribers	Behaviors	Media & Entertainment		Household	Modeled	20,99	44,08	Households that Alliant has identified to be loyal in their continued subscription to Redbox. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
637.038	Single Streaming Service	TV Subscribers	Behaviors	Media & Entertainment		Household	Modeled	24,88	52,24	Households that Alliant has identified to be subscribed to only a single streaming service. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
637.033	Streaming Switchers from Apple TV	TV Subscribers	Behaviors	Media & Entertainment		Household	Modeled	23,01	48,33	Households that Alliant has identified to be a switcher from Apple TV, meaning they have cancelled their subscription from Apple TV and switched to another streaming service. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
637.031	Streaming Switchers from Hulu	TV Subscribers	Behaviors	Media & Entertainment		Household	Modeled	23,67	49,70	Households that Alliant has identified to be a switcher from Hulu, meaning they have cancelled their subscription from Hulu and switched to another streaming service. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
637.030	Streaming Switchers From Netlfix	TV Subscribers	Behaviors	Media & Entertainment		Household	Modeled	22,69	47,65	Households that Alliant has identified to be a switcher from Netflix, meaning they have cancelled their subscription from Netflix and switched to another streaming service. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
637.032	Streaming Switchers from Paramount	TV Subscribers	Behaviors	Media & Entertainment		Household	Modeled	23,05	48,41	Households that Alliant has identified to be a switcher from Paramount, meaning they have cancelled their subscription from Paramount and switched to another streaming service. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
637.037	Streaming Switchers to Apple TV	TV Subscribers	Behaviors	Media & Entertainment		Household	Modeled	23,76	49,89	Households that Alliant has identified to be a switcher to Apple TV, meaning they have cancelled their subscription from another streaming service and switched to Apple TV. Identified by known e-commerce signal from monthly purchase transactions. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
637.035	Streaming Switchers to Hulu	TV Subscribers	Behaviors	Media & Entertainment		Household	Modeled	23,34	49,02	Households that Alliant has identified to be a switcher to Hulu, meaning they have cancelled their subscription from another streaming service and switched to Hulu. Identified by known e-commerce signal from monthly purchase transactions. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
637.034	Streaming Switchers to Netflix	TV Subscribers	Behaviors	Media & Entertainment		Household	Modeled	22,19	46,60	Households that Alliant has identified to be a switcher to Netflix, meaning they have cancelled their subscription from another streaming service and switched to Netflix. Identified by known e-commerce signal from monthly purchase transactions. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
637.036	Streaming Switchers to Paramount	TV Subscribers	Behaviors	Media & Entertainment		Household	Modeled	23,41	49,15	Households that Alliant has identified to be a switcher to Paramount, meaning they have cancelled their subscription from another streaming service and switched to Paramount. Identified by known e-commerce signal from monthly purchase transactions. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
229.121	Video Streaming Big Spender Propensity	TV Subscribers	Big Spenders by Brand Category	Media & Entertainment		Household	Modeled	12,04	25,28	This audience consists of households in the top 15-20% of a model predicting big spenders within the Video Streaming category. The model is built using brand specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.459	Samsung Subscriber Propensity	TV Subscribers	Electronics	Tech		Household	Modeled	15,39	32,31	This audience consists of households in the top 15-20% of a model predicting a purchase from Samsung. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.738	Cable ONE Subscriber Propensity	TV Subscribers	MVPD	Telecom		Household	Modeled	10,00	21,00	This audience consists of households in the top 15-20% of a model predicting a purchase from Cable ONE. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.739	Cablevision Subscriber Propensity	TV Subscribers	MVPD	Telecom		Household	Modeled	13,59	28,53	This audience consists of households in the top 15-20% of a model predicting a purchase from Cablevision. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.740	Charter Subscriber Propensity	TV Subscribers	MVPD	Telecom		Household	Modeled	15,00	31,49	This audience consists of households in the top 15-20% of a model predicting a purchase from Charter. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.731	Comcast Subscriber Propensity	TV Subscribers	MVPD	Telecom		Household	Modeled	14,53	30,52	This audience consists of households in the top 15-20% of a model predicting a purchase from Comcast. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.319	Cox Communications Subscriber Propensity	TV Subscribers	MVPD	Telecom		Household	Modeled	15,47	32,49	This audience consists of households in the top 15-20% of a model predicting a purchase from Cox Communications. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.742	DIRECTV Subscriber Propensity	TV Subscribers	MVPD	Telecom		Household	Modeled	13,38	28,10	This audience consists of households in the top 15-20% of a model predicting a purchase from DIRECTV. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.743	DISH Subscriber Propensity	TV Subscribers	MVPD	Telecom		Household	Modeled	10,83	22,74	This audience consists of households in the top 15-20% of a model predicting a purchase from DISH. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.089	Frontier.com Subscriber Propensity	TV Subscribers	MVPD	Telecom		Household	Modeled	14,12	29,64	This audience consists of households in the top 15-20% of a model predicting a purchase from Frontier.com. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.732	Spectrum Buyer Propensity	TV Subscribers	MVPD	Telecom		Household	Modeled	12,10	25,40	This audience consists of households in the top 15-20% of a model predicting a purchase from Spectrum. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.236	Time Warner Cable Buyer Propensity	TV Subscribers	MVPD	Telecom		Household	Modeled	16,39	34,41	This audience consists of households in the top 15-20% of a model predicting a purchase from Time Warner Cable. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.476	AMC Subscriber Propensity	TV Subscribers	Streaming Services	Media & Entertainment		Household	Modeled	14,16	29,74	This audience consists of households in the top 15-20% of a model predicting a purchase from AMC. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.511	CBS All Access Subscriber Propensity	TV Subscribers	Streaming Services	Media & Entertainment		Household	Modeled	24,38	51,20	This audience consists of households in the top 15-20% of a model predicting a purchase from CBS All Access. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.302	Crunchyroll Subscriber Propensity	TV Subscribers	Streaming Services	Media & Entertainment		Household	Modeled	14,80	31,07	This audience consists of households in the top 15-20% of a model predicting a purchase from Crunchyroll. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.312	FuboTV Subscriber Propensity	TV Subscribers	Streaming Services	Media & Entertainment		Household	Modeled	13,42	28,17	This audience consists of households in the top 15-20% of a model predicting a purchase from Fubo TV. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.439	HBO Max Streaming Service	TV Subscribers	Streaming Services	Media & Entertainment		Household	Modeled	17,10	35,91	This audience consists of households in the top 15-20% of a model predicting an interest in HBO Max Streaming Services. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.646	Hulu Subscriber Propensity	TV Subscribers	Streaming Services	Media & Entertainment		Household	Modeled	14,92	31,33	This audience consists of households in the top 15-20% of a model predicting a purchase from Hulu. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
637.039	Multi Streaming Services	TV Subscribers	Streaming Services	Media & Entertainment		Household	Modeled	24,28	50,99	Households that Alliant has identified to be subscribed to multiple streaming services. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.651	Netflix Subscriber Propensity	TV Subscribers	Streaming Services	Media & Entertainment		Household	Modeled	14,79	31,06	This audience consists of households in the top 15-20% of a model predicting a purchase from Netflix. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
13.613	Online Streaming and Devices Propensity	TV Subscribers	Streaming Services	Media & Entertainment		Household	Modeled	10,71	22,50	This audience consists of households in the top 20% of a model predicting the likelihood that they frequently purchase/rent videos online and use internet video devices such as: Smart TV, Apple TV, Google Chromecast, Roku, Sling, Google TV, etc. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
226.444	Peacock Streaming Service	TV Subscribers	Streaming Services	Media & Entertainment		Household	Modeled	15,62	32,80	This audience consists of households in the top 15-20% of a model predicting an interest in Peacock Streaming Services. The model is built using Twitter data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
294.334	Philo Subscriber Propensity	TV Subscribers	Streaming Services	Media & Entertainment		Household	Modeled	11,35	23,84	This audience consists of households in the top 15-20% of a model predicting a purchase from Philo. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.655	Redbox Subscriber Propensity	TV Subscribers	Streaming Services	Media & Entertainment		Household	Modeled	11,21	23,55	This audience consists of households in the top 15-20% of a model predicting a purchase from Redbox. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
12.458	Roku Subscriber Propensity	TV Subscribers	Streaming Services	Media & Entertainment		Household	Modeled	12,83	26,93	This audience consists of households in the top 15-20% of a model predicting a purchase from Roku. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
226.398	Tubi Streaming Service	TV Subscribers	Streaming Services	Media & Entertainment		Household	Modeled	13,98	29,35	This audience consists of households in the top 15-20% of a model predicting they have an interest in Tubi Streaming Service. The model is built using survey data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The combined data identifies households in the cooperative that have shared characteristics.
226.552	YouTube Subscriber Propensity	TV Subscribers	Streaming Services	Media & Entertainment		Household	Modeled	21,86	45,91	This audience consists of households in the top 15-20% of a model predicting a purchase from YouTube. The model is built using brand-specific e-commerce data as a study group, that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.778	Action Adventure Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,81	39,50	This audience consists of households in the top 15-20% of a model predicting Action-Adventure genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.779	Action Animation Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,62	39,10	This audience consists of households in the top 15-20% of a model predicting Action-Animation genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.780	Action Comedy Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,59	39,03	This audience consists of households in the top 15-20% of a model predicting Action-Comedy genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.781	Action Crime Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,59	39,03	This audience consists of households in the top 15-20% of a model predicting Action-Crime genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.782	Action Drama Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,59	39,04	This audience consists of households in the top 15-20% of a model predicting Action-Drama genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.783	Action Fantasy Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,37	38,58	This audience consists of households in the top 15-20% of a model predicting Action-Fantasy genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.784	Action Mystery Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,43	38,69	This audience consists of households in the top 15-20% of a model predicting Action-Mystery genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.785	Action Thriller Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,47	38,79	This audience consists of households in the top 15-20% of a model predicting Action-Thriller genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.286	Action Viewer	TV Viewership	Genre	Media & Entertainment		Household	Known	10,51	22,06	This audience consists of households with “known” Action viewership activity. The audience is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.
658.777	Action Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	19,10	40,11	This audience consists of households in the top 15-20% of a model predicting Action genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.786	Adult Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,90	39,68	This audience consists of households in the top 15-20% of a model predicting Adult genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.788	Adventure Animation Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,02	37,84	This audience consists of households in the top 15-20% of a model predicting Adventure-Animation genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.789	Adventure Comedy Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	17,92	37,63	This audience consists of households in the top 15-20% of a model predicting Adventure-Comedy genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.790	Adventure Drama Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	17,92	37,63	This audience consists of households in the top 15-20% of a model predicting Adventure-Drama genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.791	Adventure Family Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	17,81	37,41	This audience consists of households in the top 15-20% of a model predicting Adventure-Family genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.287	Adventure Viewer	TV Viewership	Genre	Media & Entertainment		Household	Known	10,17	21,35	This audience consists of households with “known” Adventure viewership activity. The audience is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.
658.787	Adventure Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	19,09	40,09	This audience consists of households in the top 15-20% of a model predicting Adventure genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.795	Animation Comedy Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,68	39,22	This audience consists of households in the top 15-20% of a model predicting Animation-Comedy genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.796	Animation Drama Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,66	39,18	This audience consists of households in the top 15-20% of a model predicting Animation-Drama genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.288	Animation Viewer	TV Viewership	Genre	Media & Entertainment		Household	Known	8,18	17,19	This audience consists of households with “known” Animation viewership activity. The audience is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.
658.794	Animation Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	19,14	40,19	This audience consists of households in the top 15-20% of a model predicting Animation genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.806	Biography Comedy Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	17,62	37,00	This audience consists of households in the top 15-20% of a model predicting Biography-Comedy genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.807	Biography Crime Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	17,48	36,71	This audience consists of households in the top 15-20% of a model predicting Biography-Crime genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.808	Biography Documentary Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	17,60	36,95	This audience consists of households in the top 15-20% of a model predicting Biography-Documentary genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.809	Biography Drama Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	17,56	36,88	This audience consists of households in the top 15-20% of a model predicting Biography-Drama genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.289	Biography Viewer	TV Viewership	Genre	Media & Entertainment		Household	Known	4,77	10,03	This audience consists of households with “known” Biography viewership activity. The audience is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.
658.805	Biography Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	19,20	40,31	This audience consists of households in the top 15-20% of a model predicting Biography genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.820	Comedy Crime Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,61	39,08	This audience consists of households in the top 15-20% of a model predicting Comedy-Crime genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.821	Comedy Drama Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,65	39,17	This audience consists of households in the top 15-20% of a model predicting Comedy-Drama genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.822	Comedy Family Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,59	39,04	This audience consists of households in the top 15-20% of a model predicting Comedy-Family genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.823	Comedy Fantasy Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,53	38,92	This audience consists of households in the top 15-20% of a model predicting Comedy-Fantasy genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.824	Comedy Horror Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,55	38,95	This audience consists of households in the top 15-20% of a model predicting Comedy-Horror genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.825	Comedy Romance Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,64	39,15	This audience consists of households in the top 15-20% of a model predicting Comedy-Romance genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.290	Comedy Viewer	TV Viewership	Genre	Media & Entertainment		Household	Known	9,79	20,57	This audience consists of households with “known” Comedy viewership activity. The audience is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.
658.819	Comedy Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	19,12	40,14	This audience consists of households in the top 15-20% of a model predicting Comedy genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.828	Crime Documentary Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	17,05	35,80	This audience consists of households in the top 15-20% of a model predicting Crime-Documentary genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.829	Crime Drama Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	17,06	35,82	This audience consists of households in the top 15-20% of a model predicting Crime-Drama genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.291	Crime Viewer	TV Viewership	Genre	Media & Entertainment		Household	Known	8,13	17,06	This audience consists of households with “known” Crime viewership activity. The audience is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.
658.827	Crime Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	19,13	40,18	This audience consists of households in the top 15-20% of a model predicting Crime genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.835	Documentary History Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,14	38,10	This audience consists of households in the top 15-20% of a model predicting Documentary-History genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.836	Documentary Music Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,26	38,34	This audience consists of households in the top 15-20% of a model predicting Documentary-Music genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.837	Documentary Sport Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,24	38,31	This audience consists of households in the top 15-20% of a model predicting Documentary-Sport genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.293	Documentary Viewer	TV Viewership	Genre	Media & Entertainment		Household	Known	3,16	6,63	This audience consists of households with “known” Documentary viewership activity. The audience is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.
658.834	Documentary Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	19,00	39,89	This audience consists of households in the top 15-20% of a model predicting Documentary genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.840	Drama Fantasy Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,68	39,23	This audience consists of households in the top 15-20% of a model predicting Drama-Fantasy genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.841	Drama History Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,64	39,13	This audience consists of households in the top 15-20% of a model predicting Drama-History genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.842	Drama Horror Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,66	39,18	This audience consists of households in the top 15-20% of a model predicting Drama-Horror genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.843	Drama Mystery Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,70	39,28	This audience consists of households in the top 15-20% of a model predicting Drama-Mystery genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.844	Drama Romance Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,62	39,10	This audience consists of households in the top 15-20% of a model predicting Drama-Romance genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.845	Drama Sci-Fi Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,80	39,48	This audience consists of households in the top 15-20% of a model predicting Drama-Sci-Fi genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.846	Drama Sport Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,38	38,61	This audience consists of households in the top 15-20% of a model predicting Drama-Sport genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.847	Drama Thriller Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,69	39,26	This audience consists of households in the top 15-20% of a model predicting Drama-Thriller genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.294	Drama Viewer	TV Viewership	Genre	Media & Entertainment		Household	Known	10,46	21,96	This audience consists of households with “known” Drama viewership activity. The audience is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.
658.839	Drama Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	19,09	40,09	This audience consists of households in the top 15-20% of a model predicting Drama genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.848	Drama Western Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,63	39,12	This audience consists of households in the top 15-20% of a model predicting Drama-Western genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.295	Family Viewer	TV Viewership	Genre	Media & Entertainment		Household	Known	4,71	9,89	This audience consists of households with “known” Family viewership activity. The audience is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.
658.851	Family Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,84	39,57	This audience consists of households in the top 15-20% of a model predicting Family genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.854	Fantasy Horror Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	17,97	37,73	This audience consists of households in the top 15-20% of a model predicting Fantasy-Horror genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.296	Fantasy Viewer	TV Viewership	Genre	Media & Entertainment		Household	Known	7,40	15,55	This audience consists of households with “known” Fantasy viewership activity. The audience is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.
658.853	Fantasy Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,81	39,51	This audience consists of households in the top 15-20% of a model predicting Fantasy genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.856	Film-Noir Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,58	39,01	This audience consists of households in the top 15-20% of a model predicting Film-Noir genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.863	Game-Show Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,95	39,79	This audience consists of households in the top 15-20% of a model predicting Game-Show genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.297	History Viewer	TV Viewership	Genre	Media & Entertainment		Household	Known	4,22	8,87	This audience consists of households with “known” History viewership activity. The audience is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.
658.867	History Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,65	39,16	This audience consists of households in the top 15-20% of a model predicting History genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.869	Horror Mystery Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	17,81	37,40	This audience consists of households in the top 15-20% of a model predicting Horror-Mystery genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.870	Horror Sci-Fi Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	17,77	37,32	This audience consists of households in the top 15-20% of a model predicting Horror-Sci-Fi genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.871	Horror Thriller Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	17,82	37,43	This audience consists of households in the top 15-20% of a model predicting Horror-Thriller genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.298	Horror Viewer	TV Viewership	Genre	Media & Entertainment		Household	Known	6,77	14,22	This audience consists of households with “known” Horror viewership activity. The audience is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.
658.868	Horror Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,85	39,59	This audience consists of households in the top 15-20% of a model predicting Horror genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.299	Music Viewer	TV Viewership	Genre	Media & Entertainment		Household	Known	3,57	7,49	This audience consists of households with “known” Music viewership activity. The audience is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.
658.887	Music Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	19,06	40,03	This audience consists of households in the top 15-20% of a model predicting Music genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.888	Musical Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	17,94	37,68	This audience consists of households in the top 15-20% of a model predicting Musical genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.300	Mystery Viewer	TV Viewership	Genre	Media & Entertainment		Household	Known	6,46	13,57	This audience consists of households with “known” Mystery viewership activity. The audience is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.
658.889	Mystery Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	19,19	40,30	This audience consists of households in the top 15-20% of a model predicting Mystery genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.891	News Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,42	38,68	This audience consists of households in the top 15-20% of a model predicting News genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.302	Reality-TV Viewer	TV Viewership	Genre	Media & Entertainment		Household	Known	3,03	6,36	This audience consists of households with “known” Reality TV viewership activity. The audience is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.
658.900	Reality-TV Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,73	39,34	This audience consists of households in the top 15-20% of a model predicting Reality-TV genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.303	Romance Viewer	TV Viewership	Genre	Media & Entertainment		Household	Known	5,63	11,82	This audience consists of households with “known” Romance viewership activity. The audience is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.
658.903	Romance Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	19,06	40,02	This audience consists of households in the top 15-20% of a model predicting Romance genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.906	Sci-Fi Thriller Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,82	39,53	This audience consists of households in the top 15-20% of a model predicting Sci-Fi-Thriller genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.304	Sci-Fi Viewer	TV Viewership	Genre	Media & Entertainment		Household	Known	7,11	14,92	This audience consists of households with “known” Sci-Fi viewership activity. The audience is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.
658.905	Sci-Fi Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,82	39,51	This audience consists of households in the top 15-20% of a model predicting Sci-Fi genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.914	Short Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	17,94	37,68	This audience consists of households in the top 15-20% of a model predicting Short genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.305	Sport Viewer	TV Viewership	Genre	Media & Entertainment		Household	Known	2,99	6,28	This audience consists of households with “known” Sport viewership activity. The audience is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.
658.919	Sport Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,99	39,87	This audience consists of households in the top 15-20% of a model predicting Sport genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.928	Talk-Show Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,79	39,47	This audience consists of households in the top 15-20% of a model predicting Talk-Show genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.306	Thriller Viewer	TV Viewership	Genre	Media & Entertainment		Household	Known	8,05	16,90	This audience consists of households with “known” Thriller viewership activity. The audience is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.
658.954	Thriller Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,98	39,86	This audience consists of households in the top 15-20% of a model predicting Thriller genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.307	War Viewer	TV Viewership	Genre	Media & Entertainment		Household	Known	2,27	4,76	This audience consists of households with “known” War viewership activity. The audience is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.
658.965	War Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,92	39,73	This audience consists of households in the top 15-20% of a model predicting War genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.308	Western Viewer	TV Viewership	Genre	Media & Entertainment		Household	Known	2,07	4,35	This audience consists of households with “known” Western viewership activity. The audience is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.
658.967	Western Viewer Propensity	TV Viewership	Genre	Media & Entertainment		Household	Modeled	18,51	38,87	This audience consists of households in the top 15-20% of a model predicting Western genre viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.776	1923	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,41	38,66	This audience consists of households in the top 15-20% of a model predicting 1923 viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.793	Amazon Originals	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,58	36,92	This audience consists of households in the top 15-20% of a model predicting Amazon Originals viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.797	Ant-Man and the Wasp	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,38	38,60	This audience consists of households in the top 15-20% of a model predicting Ant-Man and the Wasp viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.799	Apple TV Originals	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,74	37,25	This audience consists of households in the top 15-20% of a model predicting Apple TV Originals viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.800	Avatar	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,31	38,46	This audience consists of households in the top 15-20% of a model predicting Avatar viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.801	Band of Brothers	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,60	39,07	This audience consists of households in the top 15-20% of a model predicting Band of Brothers viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.802	Based on a True Story	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	19,18	40,29	This audience consists of households in the top 15-20% of a model predicting Based on a True Story viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.803	Better Call Saul	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,91	37,62	This audience consists of households in the top 15-20% of a model predicting Better Call Saul viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.804	Big Little Lies	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	19,78	41,54	This audience consists of households in the top 15-20% of a model predicting Big Little Lies viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.810	Black Adam	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,26	36,24	This audience consists of households in the top 15-20% of a model predicting Black Adam viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.811	Black Bird	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,63	39,13	This audience consists of households in the top 15-20% of a model predicting Black Bird viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.812	Black Mirror	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,35	38,54	This audience consists of households in the top 15-20% of a model predicting Black Mirror viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.813	Black Panther	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,38	38,59	This audience consists of households in the top 15-20% of a model predicting Black Panther viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.814	Bridgerton	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	14,23	29,88	This audience consists of households in the top 15-20% of a model predicting Bridgerton viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.815	Bullet Train	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,31	36,35	This audience consists of households in the top 15-20% of a model predicting Bullet Train viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.816	Bupkis	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,56	38,97	This audience consists of households in the top 15-20% of a model predicting Bupkis viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.817	Chernobyl	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,07	37,94	This audience consists of households in the top 15-20% of a model predicting Chernobyl viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.818	Clarksons Farm	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,14	38,09	This audience consists of households in the top 15-20% of a model predicting Clarksons Farm viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.826	Creed III	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,03	37,86	This audience consists of households in the top 15-20% of a model predicting Creed III viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.830	Criminal Minds	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,16	38,13	This audience consists of households in the top 15-20% of a model predicting Criminal Minds viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.831	Cruel Summer	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	19,18	40,27	This audience consists of households in the top 15-20% of a model predicting Cruel Summer viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.832	Deadpool	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,49	36,73	This audience consists of households in the top 15-20% of a model predicting Deadpool viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.833	Demon Slayer Kimetsu no Yaiba	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,45	38,74	This audience consists of households in the top 15-20% of a model predicting Demon Slayer Kimetsu no Yaiba viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.838	Downton Abbey	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,34	38,51	This audience consists of households in the top 15-20% of a model predicting Downton Abbey viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.849	Dungeons and Dragons	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,35	38,54	This audience consists of households in the top 15-20% of a model predicting Dungeons and Dragons viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.850	Euphoria	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,69	37,15	This audience consists of households in the top 15-20% of a model predicting Euphoria viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.852	Family Guy	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,12	38,05	This audience consists of households in the top 15-20% of a model predicting Family Guy viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.855	Fast X	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,02	37,84	This audience consists of households in the top 15-20% of a model predicting Fast X viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.857	For All Mankind	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,23	38,28	This audience consists of households in the top 15-20% of a model predicting For All Mankind viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.858	Formula 1	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,83	39,55	This audience consists of households in the top 15-20% of a model predicting Formula 1 viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.859	Foundation	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,44	38,73	This audience consists of households in the top 15-20% of a model predicting Foundation viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.860	From	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,43	38,71	This audience consists of households in the top 15-20% of a model predicting From viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.861	Futurama	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,51	38,87	This audience consists of households in the top 15-20% of a model predicting Futurama viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.862	Game of Thrones	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,92	37,64	This audience consists of households in the top 15-20% of a model predicting Game of Thrones viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.865	Guardians of the Galaxy	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,02	37,85	This audience consists of households in the top 15-20% of a model predicting Guardians of the Galaxy viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.866	HBO Max Originals	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,73	37,23	This audience consists of households in the top 15-20% of a model predicting HBO Max Originals viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.872	House of the Dragon	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,40	38,64	This audience consists of households in the top 15-20% of a model predicting House of the Dragon viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.873	Hulu Originals	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,67	37,10	This audience consists of households in the top 15-20% of a model predicting Hulu Originals viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.874	Its Always Sunny in Philadelphia	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,32	38,47	This audience consists of households in the top 15-20% of a model predicting Its Always Sunny in Philadelphia viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.956	Jack Ryan	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,36	38,55	This audience consists of households in the top 15-20% of a model predicting Jack Ryan viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.875	John Wick	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,41	38,67	This audience consists of households in the top 15-20% of a model predicting John Wick viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.876	Jurassic World	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,18	36,08	This audience consists of households in the top 15-20% of a model predicting Jurassic World viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.877	La Brea	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,15	38,11	This audience consists of households in the top 15-20% of a model predicting La Brea viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.879	Lord of the Rings	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,40	38,64	This audience consists of households in the top 15-20% of a model predicting Lord of the Rings viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.880	Love Island	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,85	37,48	This audience consists of households in the top 15-20% of a model predicting Love Island viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.881	Lupin	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	19,92	41,83	This audience consists of households in the top 15-20% of a model predicting Lupin viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.882	Manifest	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,22	38,26	This audience consists of households in the top 15-20% of a model predicting Manifest viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.883	Money Heist	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,76	37,30	This audience consists of households in the top 15-20% of a model predicting Money Heist viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.886	Mrs. Davis	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,38	38,59	This audience consists of households in the top 15-20% of a model predicting Mrs. Davis viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.890	Netflix Originals	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,64	37,04	This audience consists of households in the top 15-20% of a model predicting Netflix Originals viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.892	Outer Banks	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,85	37,48	This audience consists of households in the top 15-20% of a model predicting Outer Banks viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.893	Outlander	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,24	38,30	This audience consists of households in the top 15-20% of a model predicting Outlander viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.894	Ozark	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,39	36,52	This audience consists of households in the top 15-20% of a model predicting Ozark viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.895	Peacock Originals	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,60	36,95	This audience consists of households in the top 15-20% of a model predicting Peacock Originals viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.896	Peaky Blinders	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,45	36,64	This audience consists of households in the top 15-20% of a model predicting Peaky Blinders viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.897	Poker Face	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,31	38,45	This audience consists of households in the top 15-20% of a model predicting Poker Face viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.898	Puss in Boots	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,45	38,74	This audience consists of households in the top 15-20% of a model predicting Puss in Boots viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.899	Reacher	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,71	37,19	This audience consists of households in the top 15-20% of a model predicting Reacher viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.901	Rick and Morty	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,40	38,64	This audience consists of households in the top 15-20% of a model predicting Rick and Morty viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.907	Scream 6	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,30	38,43	This audience consists of households in the top 15-20% of a model predicting Scream 6 viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.908	Secret Invasion	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,28	38,39	This audience consists of households in the top 15-20% of a model predicting Secret Invasion viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.909	See	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,19	38,20	This audience consists of households in the top 15-20% of a model predicting See viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.910	Servant	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,31	38,46	This audience consists of households in the top 15-20% of a model predicting Servant viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.911	Severance	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,95	37,69	This audience consists of households in the top 15-20% of a model predicting Severance viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.912	Shazam Fury of the Gods	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,31	38,45	This audience consists of households in the top 15-20% of a model predicting Shazam Fury of the Gods viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.913	She-Hulk	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,20	38,21	This audience consists of households in the top 15-20% of a model predicting She-Hulk viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.915	Slow Horses	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,56	38,97	This audience consists of households in the top 15-20% of a model predicting Slow Horses viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.917	South Park	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,48	38,80	This audience consists of households in the top 15-20% of a model predicting South Park viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.918	Spider-Man	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,02	37,84	This audience consists of households in the top 15-20% of a model predicting Spider-Man viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.920	Squid Game	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,89	37,57	This audience consists of households in the top 15-20% of a model predicting Squid Game viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.921	Star Trek	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,44	38,72	This audience consists of households in the top 15-20% of a model predicting Star Trek viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.922	Stranger Things	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,50	36,74	This audience consists of households in the top 15-20% of a model predicting Stranger Things viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.923	Succession	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,48	38,81	This audience consists of households in the top 15-20% of a model predicting Succession viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.924	Suits	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,59	39,05	This audience consists of households in the top 15-20% of a model predicting Suits viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.925	Supernatural	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,56	36,88	This audience consists of households in the top 15-20% of a model predicting Supernatural viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.926	Superstore	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	14,23	29,88	This audience consists of households in the top 15-20% of a model predicting Superstore viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.927	Survivor	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,19	38,20	This audience consists of households in the top 15-20% of a model predicting Survivor viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.929	Ted Lasso	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,52	38,90	This audience consists of households in the top 15-20% of a model predicting Ted Lasso viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.930	Teen Titans Go	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,07	37,96	This audience consists of households in the top 15-20% of a model predicting Teen Titans Go viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.931	The Ark	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,09	37,99	This audience consists of households in the top 15-20% of a model predicting The Ark viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.932	The Bachelorette	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,41	38,66	This audience consists of households in the top 15-20% of a model predicting The Bachelorette viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.933	The Big Bang Theory	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,85	37,49	This audience consists of households in the top 15-20% of a model predicting The Big Bang Theory viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.934	The Boys	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,77	37,32	This audience consists of households in the top 15-20% of a model predicting The Boys viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.935	The Flash	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,03	37,86	This audience consists of households in the top 15-20% of a model predicting The Flash viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.884	The Jeffrey Dahmer Story	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,99	37,78	This audience consists of households in the top 15-20% of a model predicting The Jeffrey Dahmer Story viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.936	The Last of Us	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,57	39,00	This audience consists of households in the top 15-20% of a model predicting The Last of Us viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.937	The Little Mermaid	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,80	37,38	This audience consists of households in the top 15-20% of a model predicting The Little Mermaid viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.938	The Mandalorian	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,61	39,08	This audience consists of households in the top 15-20% of a model predicting The Mandalorian viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.939	The Morning Show	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,57	39,00	This audience consists of households in the top 15-20% of a model predicting The Morning Show viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.940	The Night Agent	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,19	38,20	This audience consists of households in the top 15-20% of a model predicting The Night Agent viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.941	The Peripheral	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,48	38,80	This audience consists of households in the top 15-20% of a model predicting The Peripheral viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.942	The Queens Gambit	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,63	39,12	This audience consists of households in the top 15-20% of a model predicting The Queens Gambit viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.943	The Rookie	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,22	38,25	This audience consists of households in the top 15-20% of a model predicting The Rookie viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.944	The Simpsons	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,38	38,59	This audience consists of households in the top 15-20% of a model predicting The Simpsons viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.945	The Sopranos	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,21	38,24	This audience consists of households in the top 15-20% of a model predicting The Sopranos viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.946	The Summer I Turned Pretty	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	19,14	40,20	This audience consists of households in the top 15-20% of a model predicting The Summer I Turned Pretty viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.947	The Super Mario Bros Movie	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,43	38,71	This audience consists of households in the top 15-20% of a model predicting The Super Mario Bros Movie viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.948	The Terminal List	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,67	39,21	This audience consists of households in the top 15-20% of a model predicting The Terminal List viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.949	The Walking Dead	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,18	38,19	This audience consists of households in the top 15-20% of a model predicting The Walking Dead viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.950	The Wheel of Time	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,12	38,06	This audience consists of households in the top 15-20% of a model predicting The Wheel of Time viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.951	The Wire	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,56	38,97	This audience consists of households in the top 15-20% of a model predicting The Wire viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.952	The Witcher	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,34	38,52	This audience consists of households in the top 15-20% of a model predicting The Witcher viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.953	Thor	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,29	36,31	This audience consists of households in the top 15-20% of a model predicting Thor viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.957	Top Gun	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,30	36,32	This audience consists of households in the top 15-20% of a model predicting Top Gun viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.958	Transformers	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,00	37,80	This audience consists of households in the top 15-20% of a model predicting Transformers viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.959	True Detective	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,39	36,51	This audience consists of households in the top 15-20% of a model predicting True Detective viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.960	Tulsa King	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,44	38,73	This audience consists of households in the top 15-20% of a model predicting Tulsa King viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.961	Twisted Metal	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,09	37,99	This audience consists of households in the top 15-20% of a model predicting Twisted Metal viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.962	Vampire Academy	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,13	38,08	This audience consists of households in the top 15-20% of a model predicting Vampire Academy viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.966	Wednesday	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,41	38,67	This audience consists of households in the top 15-20% of a model predicting Wednesday viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.968	Westworld	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,89	37,58	This audience consists of households in the top 15-20% of a model predicting Westworld viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.969	WWE Raw	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	17,71	37,20	This audience consists of households in the top 15-20% of a model predicting WWE Raw viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.970	Yellowstone	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,57	39,01	This audience consists of households in the top 15-20% of a model predicting Yellowstone viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.971	You	TV Viewership	Movies & Shows	Media & Entertainment		Household	Modeled	18,06	37,92	This audience consists of households in the top 15-20% of a model predicting You viewership. The model is built using viewership data sourced from smart TV manufacturers that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.309	Amazon TV Owner	TV Viewership	Smart TV Manufacturer	Media & Entertainment		Household	Known	2,77	5,82	This audience consists of households with “known” Amazon smart TV ownership. The audience is built using data sourced from the TV manufacturer that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.
658.792	Amazon TV Owner Propensity	TV Viewership	Smart TV Manufacturer	Media & Entertainment		Household	Modeled	19,56	41,08	This audience consists of households in the top 15-20% of a model predicting Amazon smart TV ownership. The model is built using data sourced from the TV manufacturer that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.311	Apple TV Owner	TV Viewership	Smart TV Manufacturer	Media & Entertainment		Household	Known	7,12	14,96	This audience consists of households with “known” Apple smart TV ownership. The audience is built using data sourced from the TV manufacturer that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.
658.798	Apple TV Owner Propensity	TV Viewership	Smart TV Manufacturer	Media & Entertainment		Household	Modeled	19,45	40,84	This audience consists of households in the top 15-20% of a model predicting Apple smart TV ownership. The model is built using data sourced from the TV manufacturer that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.864	Google TV Owner Propensity	TV Viewership	Smart TV Manufacturer	Media & Entertainment		Household	Modeled	19,25	40,43	This audience consists of households in the top 15-20% of a model predicting Google smart TV ownership. The model is built using data sourced from the TV manufacturer that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.878	LG TV Owner Propensity	TV Viewership	Smart TV Manufacturer	Media & Entertainment		Household	Modeled	19,56	41,07	This audience consists of households in the top 15-20% of a model predicting LG smart TV ownership. The model is built using data sourced from the TV manufacturer that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.885	Motorola TV Owner Propensity	TV Viewership	Smart TV Manufacturer	Media & Entertainment		Household	Modeled	19,41	40,76	This audience consists of households in the top 15-20% of a model predicting Motorola smart TV ownership. The model is built using data sourced from the TV manufacturer that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.310	Roku TV Owner	TV Viewership	Smart TV Manufacturer	Media & Entertainment		Household	Known	7,05	14,80	This audience consists of households with “known” Roku smart TV ownership. The audience is built using data sourced from the TV manufacturer that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.
658.902	Roku TV Owner Propensity	TV Viewership	Smart TV Manufacturer	Media & Entertainment		Household	Modeled	19,72	41,42	This audience consists of households in the top 15-20% of a model predicting Roku smart TV ownership. The model is built using data sourced from the TV manufacturer that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.312	Samsung TV Owner	TV Viewership	Smart TV Manufacturer	Media & Entertainment		Household	Known	7,21	15,13	This audience consists of households with “known” Samsung smart TV ownership. The audience is built using data sourced from the TV manufacturer that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information.
658.904	Samsung TV Owner Propensity	TV Viewership	Smart TV Manufacturer	Media & Entertainment		Household	Modeled	19,68	41,32	This audience consists of households in the top 15-20% of a model predicting Samsung smart TV ownership. The model is built using data sourced from the TV manufacturer that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.916	Sony TV Owner Propensity	TV Viewership	Smart TV Manufacturer	Media & Entertainment		Household	Modeled	19,37	40,67	This audience consists of households in the top 15-20% of a model predicting Sony smart TV ownership. The model is built using data sourced from the TV manufacturer that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.955	Tivo TV Owner Propensity	TV Viewership	Smart TV Manufacturer	Media & Entertainment		Household	Modeled	18,97	39,83	This audience consists of households in the top 15-20% of a model predicting Tivo smart TV ownership. The model is built using data sourced from the TV manufacturer that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.963	Vivo TV Owner Propensity	TV Viewership	Smart TV Manufacturer	Media & Entertainment		Household	Modeled	19,41	40,76	This audience consists of households in the top 15-20% of a model predicting Vivo smart TV ownership. The model is built using data sourced from the TV manufacturer that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
658.964	Vizio TV Owner Propensity	TV Viewership	Smart TV Manufacturer	Media & Entertainment		Household	Modeled	19,43	40,81	This audience consists of households in the top 15-20% of a model predicting Vizio smart TV ownership. The model is built using data sourced from the TV manufacturer that is then joined to an offline cooperative database of direct-to-consumer purchase transactions, demographics and lifestyle information. The analysis of the combined data is used for predictive modeling to identify other households in the cooperative that have shared characteristics.
MDM ID	Segment	Category	Sub-Category	Vertical 1	Vertical 2	HH/Ind		Audience Size (PII)

Audiences Where You Need Them

You need to be free to reach the right audience, at the right time, regardless of channel. We’ve built a massive database of billions of match keys so we can help you execute on that vision. Whatever the requirement, be it postal, email, IP or lat/long, we handle distribution so that you can execute.

Future-Proofed Delivery

Alliant solutions are built on top of an extensive identity graph, guaranteeing flexible connection and distribution options across channels.

Addressable TV

Programmatic

Social

CDPs & Analytic Platforms

Direct Mail

Data Help Desk.

Need a custom audience, recommendations on audience strategy, or assistance on a proposal? Our team is always available to consult on your specific data needs.

“Alliant has been an amazing partner. Their service is unmatched whether you’re looking for guidance on targeting segments or just have random questions. We look forward to continuing our partnership with Alliant!”

Stephanie Foster

Advanced TV Sales Director, East – Verizon Media

By submitting my data I agree to be contacted

The DataHub

Audience Solutions

Alliant Serves

Audience Guides

Trending

WEBINAR RECORDING

Explore

Success Stories

Latest Posts

About Alliant

Great People. Great Data. Great Results.

Data Governance

Complianceby Design

Join the Team

follow us