Behavioral targeting system that generates user profiles for target objectives
A behavioral targeting system determines user profiles from online activity. The system includes a plurality of models that define parameters for determining a user profile score. Event information, which comprises on-line activity of the user, is received at an entity. To generate a user profile score, a model is selected. The model comprises recency, intensity and frequency dimension parameters. The behavioral targeting system generates a user profile score for a target objective, such as brand advertising or direct response advertising. The parameters from the model are applied to generate the user profile score in a category. The behavioral targeting system has application for use in ad serving to on-line users.
1. A computer-implemented method for utilizing at least a computer processor for determining user behavior from online activity, said method comprising:
processing a user data set, comprising past event information from a plurality of events, compiled from past on-line activity between users of said user data set and an entity;
analyzing said user data set to ascertain a level of performance of said past event information to predict said user behavior for each of a plurality of targeting objectives comprising at least two of direct response advertising, purchase intention, branding advertising, personalization, and intra company business unit marketing;
generating a plurality of models, one for each of said targeting objectives, wherein each model comprises a plurality of weights for determining a user interest score for a corresponding targeting objective;
generating said weights for said models by ascribing a prediction value to said past event information in accordance with said level of performance of said past event information for said corresponding targeting objective;
storing said models for said targeting objectives;
receiving, at said entity, additional event information from at least one event from a user; and
generating said user interest score for said user for one of said targeting objectives using a corresponding model for said targeting objective by applying at least one weight from said corresponding model based on said additional event information to predict said user's propensity for success in said targeting objective.
2. The method as set forth in claim 1 , wherein said targeting objective comprises a marketing objective.
3. The method as set forth in claim 2 , wherein said marketing objective comprises brand awareness.
4. The method as set forth in claim 2 , wherein said marketing objective comprises direct response advertising.
5. The method as set forth in claim 4 , wherein said direct response advertising marketing objective comprises user acquisition.
6. The method as set forth in claim 4 , wherein said direct response advertising marketing objective comprises user retention.
7. The method as set forth in claim 4 , wherein said direct response advertising marketing objective comprises engagement.
8. The method as set forth in claim 4 , wherein said direct response advertising marketing objective comprises monetization.
9. A system for determining user behavior from online activity, said system comprising:
at least one server computer, coupled to a storage, for:
processing a user data set, comprising past event information from a plurality of events, compiled from past online activity between users of said user data set and an entity,
analyzing said user data set to ascertain a level of performance of said past event information to predict said user behavior for each of a plurality of targeting objectives comprising at least two of direct response advertising, purchase intention, branding advertising, personalization, and intra company business unit marketing,
generating a plurality of models, one for each of said targeting objectives, wherein each model comprises a plurality of weights for determining a user interest score for a corresponding targeting objective, and
generating said weights for said models by ascribing a prediction value to said past event information in accordance with said level of performance of said past event information for said corresponding targeting objective;
said storage for storing said model for said targeting objectives; and said server computer, further for:
receiving additional event information from at least one event from a user, and
generating said user interest score for said user for one of said targeting objectives using a corresponding model for said targeting objective by applying at least one weight from said corresponding model based on said additional event information to predict said user's propensity for success in said targeting objective.
10. The system as set forth in claim 9 , wherein said targeting objective comprises a marketing objective.
11. The system as set forth in claim 10 , wherein said marketing objective comprises brand awareness.
12. The system as set forth in claim 10 , wherein said marketing objective comprises direct response advertising.
13. The system as set forth in claim 12 , wherein said direct response advertising marketing objective comprises user acquisition.
14. The system as set forth in claim 12 , wherein said direct response advertising marketing objective comprises user retention.
15. The system as set forth in claim 12 , wherein said direct response advertising marketing objective comprises engagement.
16. The system as set forth in claim 12 , wherein said direct response advertising marketing objective comprises monetization.
17. A non-transitory computer readable storage medium comprising a set of instructions which, when executed by a computer, causes said computer to analyze user behavior from online activity, said instructions for:
processing a user data set, comprising past event information from a plurality of events, compiled from past on-line activity between users of said user data set and an entity;
analyzing said user data set to ascertain a level of performance of said past event information to predict said user behavior for each of a plurality of targeting objectives comprising at least two of direct response advertising, purchase intention, branding advertising, personalization, and intra company business unit marketing;
generating a plurality of models, one for each of said targeting objectives, wherein each model comprises a plurality of weights for determining a user interest score for a corresponding targeting objective;
generating said weights for said models by ascribing a prediction value to said past event information in accordance with said level of performance of said past event information for said corresponding targeting objective;
storing said models for said targeting objectives;
receiving, at said entity, additional event information from at least one event from a user; and
generating said user interest score for said user for one of said targeting objectives using a corresponding model for said targeting objective by applying at least one weight from said corresponding model based on said additional event information to predict said user's propensity for success in said targeting objective.
18. The non-transitory computer readable storage medium as set forth in claim 17 , wherein said targeting objective comprises a marketing objective.
19. The non-transitory computer readable storage medium as set forth in claim 17 , wherein said marketing objective comprises brand awareness.
20. The non-transitory computer readable storage medium as set forth in claim 17 , wherein said marketing objective comprises direct response advertising.