Inferring household income for users of a social networking system

• US 8,583,471 B1
• Filed: 12/27/2011
• Issued: 11/12/2013
• Est. Priority Date: 06/13/2011
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Voskuhl, Justin B., Vyaghrapuri, Ramesh
• Primary Examiner(s): Rines, David
• Assistant Examiner(s): Gurski, Amanda
• Application Number:
  US13/338,174
• Time in Patent Office: 686 Days
• Field of Search: 705/7.33, 705/14.53
• US Class Current: 705/7.33
• CPC Class Codes: G06Q 30/0254 based on statistics

Abstract

Information about a set of users of a social networking system is obtained to develop a predictive model of income distribution for all users of the social networking system. This predictive model is based on selected attributes about the users (e.g., declared/profile information, user historical information, and/or social information). Users of the social networking system are mapped to a specific income bracket based on statistical correlations derived from the predictive model. Advertisements are targeted to users based on income bracket. The system may use a machine learning algorithm to analyze conversion rates of targeted advertising to retrain the predictive model.

Claims

1. A method comprising:

receiving information about users of a social networking system, the information describing connections between users of the social networking system and actions taken by users on the social networking system, and comprises for each user, an analysis of posted content by the user that indicates a higher-than-average income potential or a lower-than-average income potential as compared to other analyses of posted content by other users in the social networking system;

defining, by a computer processor, a predictive model of an income bracket of an income distribution of the users of the social networking system by selecting predictive factors based on the received information about the users in the income bracket; and

defining ranges for the income bracket based on the received information.

2. The method of claim 1, wherein the received information about the users of the social networking system includes income information.

3. The method of claim 1, wherein the received information about the users of the social networking system includes user profile information.

4. The method of claim 1, wherein the received information about the users of the social networking system includes unstructured information gathered from activity on the social networking system, the method further comprising:

performing heuristic analysis on the unstructured information to generate a new predictive factor for the predictive model; and

adding the new generated predictive factor to the predictive model.

5. The method of claim 1, wherein defining a predictive model of an income bracket further comprises:

mapping the received information to the predictive factors; and

selecting an initial set of predictive factors based on the received information.

6. The method of claim 1, further comprising:

determining coefficients for the selected predictive factors in the predictive model of the income bracket, wherein determining coefficients for the selected predictive factors in the predictive model of the income bracket further comprises;

utilizing the received information as a response in a regression model; and

calculating the coefficients using the selected predictive factors as weighted factors in the regression model.

13. The method of claim 1, wherein the actions taken by users on the social networking system are selected from a group consisting of:

commenting on a photo album, communications between users, becoming a fan of a musician, adding an event to a calendar, or interactions with advertisements on the social networking system.

14. The method of claim 1, wherein information describing connections between users of the social networking system are selected from a group consisting of:

wall posts, comments on photos, geographic places where they have been tagged together, photos in which they have both been tagged in, or strength of the connection between users.

7. A method comprising:

receiving information about a user of a social networking system, the information describing connections between users of the social networking system and actions taken by users on the social networking system;

responsive to the received information, mapping the received information about the user to predictive factors in predictive models for income brackets in the social networking system;

determining, by a computer processor, a correlation value for each income bracket for the user based on the predictive model corresponding to the income bracket;

associating the user with at least one of the income brackets based on the determined correlation values;

providing advertisements for display to the user based on the associated income brackets and determined correlation values; and

modifying the predictive model of an income bracket to include or exclude additional predictive factors based on an analysis of conversion rates of advertisements provided to users based on the income bracket.

8. The method of claim 7, wherein the received information about the users of the social networking system includes user profile information.

9. The method of claim 7, wherein the received information about the users of the social networking system includes unstructured information gathered from activity on the social networking system, the method further comprising:

performing heuristic analysis on the unstructured information to generate a new predictive factor for the predictive models; and

adding the new generated predictive factor to the predictive models.

10. The method of claim 7, wherein the received information about the users of the social networking system includes, for each user, an analysis of posted content by the user indicates a higher-than-average income potential as compared to other analyses of posted content by other users in the social networking system.

11. The method of claim 7, wherein the received information about the users of the social networking system includes, for each user, an analysis of posted content by the user indicates a lower-than-average income potential as compared to other analyses of posted content by other users in the social networking system.

12. The method of claim 7, further comprising:

discounting the pricing of advertisements based on the determined correlation values of the income brackets.