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 method of behavioral targeting comprising:
identifying, via a computing device, a user data set associated with a plurality of users, the user data set comprising past event information from a plurality of events, the past event information being generated based on past on-line activity between each user of the plurality of users and an entity, the user data set comprising categories of activities, wherein each activity of a particular user associated with the past event information is categorized within the user data set, the entity being an online entity;
analyzing, via the computing device, the user data set to determine a performance metric based upon the past event information, the determination comprising predicting user behavior responsive a targeting objective associated with the past on-line activity, the targeting objective comprising branding advertising associated with the entity;
generating, via the computing device, a model for the targeting objective, the model being based upon the performance metric and the past event information between each user and the entity;
storing, via the computing device, the model, the computing device being different from the entity;
receiving, at the computing device, an event associated with a first user, the first user being not within the plurality of users, the event comprising activity between the first user and the entity; and
generating, via the computing device, an interest score between the first user and the entity, the interest score being based upon the stored model.
2. The method of claim 1 , wherein the generation comprises applying the stored model to information associated with the event associated with the first user, wherein the applying comprises mapping success probability of the targeting objective respective to the first user.
3. The method of claim 1 , wherein the model comprises a user interest score for each user of the plurality of users, wherein the model further comprises weights associated with the targeting objective corresponding to corresponding user interest scores.
4. The method of claim 1 , further comprising:
updating the stored model for each user of the plurality of users, the updating reflecting updated recent past-online activity not previously accounted for within the model upon storing.
5. The method of claim 1 , further comprising:
generating a categorical model for each category of activity within the user data set, the categorical model based upon the past event information between each user and the entity falling within a particular category of activity; and
storing, via the computing device, the categorical model.
6. The method of claim 1 , wherein the targeting objective further comprises at least one of direct response advertising, purchase intention, personalization, and intra company business unit marketing.
7. The method of claim 1 , wherein the performance metric comprises a level of performance indicating how effective the brand advertising was in generating the past on-line activity between each user and the entity.
8. A non-transitory computer-readable storage medium tangibly encoded with computer-readable instructions, that when executed by a computing device, performs a method of behavioral targeting comprising:
identifying a user data set associated with a plurality of users, the user data set comprising past event information from a plurality of events, the past event information being generated based on past on-line activity between each user of the plurality of users and an entity, the user data set comprising categories of activities, wherein each activity of a particular user associated with the past event information is categorized within the user data set, the entity being an online entity;
analyzing the user data set to determine a performance metric based upon the past event information, the determination comprising predicting user behavior responsive a targeting objective associated with the past on-line activity, the targeting objective comprising branding advertising associated with the entity;
generating a model for the targeting objective, the model being based upon the performance metric and the past event information between each user and the entity;
storing the model via the computing device, the computing device being different from the entity;
receiving an event associated with a first user, the first user being not within the plurality of users, the event comprising activity between the first user and the entity; and
generating an interest score between the first user and the entity, the interest score being based upon the stored model.
9. The non-transitory computer-readable storage medium of claim 8 , wherein the generation comprises applying the stored model to information associated with the event associated with the first user, wherein the applying comprises mapping success probability of the targeting objective respective to the first user.
10. The non-transitory computer-readable storage medium of claim 8 , wherein the model comprises a user interest score for each user of the plurality of users, wherein the model further comprises weights associated with the targeting objective corresponding to corresponding user interest scores.
11. The non-transitory computer-readable storage medium of claim 8 , further comprising:
updating the stored model for each user of the plurality of users, the updating reflecting updated recent past-online activity not previously accounted for within the model upon storing.
12. The non-transitory computer-readable storage medium of claim 8 , further comprising:
generating a categorical model for each category of activity within the user data set, the categorical model based upon the past event information between each user and the entity falling within a particular category of activity; and
storing, via the computing device, the categorical model.
13. The non-transitory computer-readable storage medium of claim 8 , wherein the targeting objective further comprises at least one of direct response advertising, purchase intention, personalization, and intra company business unit marketing.
14. The non-transitory computer-readable storage medium of claim 8 , wherein the performance metric comprises a level of performance indicating how effective the brand advertising was in generating the past on-line activity between each user and the entity.
15. A system for behavioral targeting comprising:
at least one computing device comprising:
memory storing computer-executable instructions; and
one or more processors for executing the computer-executable instructions, comprising:
identifying a user data set associated with a plurality of users, the user data set comprising past event information from a plurality of events, the past event information being generated based on past on-line activity between each user of the plurality of users and an entity, the user data set comprising categories of activities, wherein each activity of a particular user associated with the past event information is categorized within the user data set, the entity being an online entity;
analyzing the user data set to determine a performance metric based upon the past event information, the determination comprising predicting user behavior responsive a targeting objective associated with the past on-line activity, the targeting objective comprising branding advertising associated with the entity;
generating a model for the targeting objective, the model being based upon the performance metric and the past event information between each user and the entity;
storing the model via the at least one computing device, the at least one computing device being different from the entity;
receiving an event associated with a first user, the first user being not within the plurality of users, the event comprising activity between the first user and the entity; and
generating an interest score between the first user and the entity, the interest score being based upon the stored model.
16. The system of claim 15 , further comprising:
applying the stored model to information associated with the event, wherein the applying comprises mapping success probability of the targeting objective respective to the first user.
17. The system of claim 15 , further comprising:
updating the stored model for each user of the plurality of users, the updating reflecting updated recent past-online activity not previously accounted for within the model upon storing.
18. The system of claim 15 , further comprising:
generating a categorical model for each category of activity within the user data set, the categorical model based upon the past event information between each user and the entity falling within a particular category of activity; and
storing, via the at least one computing device, the categorical model.