METHOD AND APPARATUS TO IDENTIFY INFLUENCERS

• US 20090063254A1
• Filed: 08/20/2008
• Published: 03/05/2009
• Est. Priority Date: 08/24/2007
• Status: Active Grant

• Current Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Paul, Deirdre, Volinsky, Christopher
• Granted Patent: US 9,946,975 B2
• Time in Patent Office: Days
• US Class Current: 705/10
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0204 Market segmentation

Abstract

A method and apparatus for identifying influencers are disclosed. For example, the method obtains a list of customers, and determines a social network for each of the customers. The method selects one or more attributes to be used for predicting a measure of influence for each of the customers, and determines one or more influencers in the social network by using the one or more attributes.

Claims

1. A method for identifying one or more influencers, comprising:

obtaining a list of customers;

determining a social network for each of said customers;

selecting one or more attributes to be used for predicting a measure of influence for each of said customers; and

determining one or more influencers in said social network by using said one or more attributes.

2. The method of claim 1, further comprising:

providing one or more actions to be taken for said one or more influencers.

3. The method of claim 1, wherein said determining said social network for each of said customers comprises:

defining a neighborhood for each of said customers;

determining a strength of relationships of each of said customers with members of said neighborhood of said customer; and

truncating said neighborhood for each of said customers by selecting k neighbors of each of said customers, wherein said k is a predetermined integer.

4. The method of claim 3, wherein said determining said social network for each of said customers further comprises:

recursively finding one or more neighborhoods for each of the remaining members in said neighborhood for a pre-determined number of times; and

defining said social network for each of said customers as the neighborhood that comprises said truncated neighborhood of said customer and the recursively found one or more neighborhoods.

5. The method of claim 3, wherein said truncating said neighborhood is performed by selecting a most important k neighbors using said strength of relationships.

6. The method of claim 1, further comprising:

Implementing a model for predicting said measure of influence for each of said customers.

7. The method of claim 6, wherein said model is a statistical model.

8. The method of claim 7, wherein said statistical model comprises at least one of:

a linear regression model, a logistic regression model, a classification model or a neural networks model.

9. The method of claim 2, wherein said one or more actions comprises one or more directing marketing actions.

10. A computer-readable medium having stored thereon a plurality of instructions, the plurality of instructions including instructions which, when executed by a processor, cause the processor to perform the steps of a method for identifying one or more influencers, comprising:

obtaining a list of customers;

determining a social network for each of said customers;

selecting one or more attributes to be used for predicting a measure of influence for each of said customers; and

determining one or more influencers in said social network by using said one or more attributes.

11. The computer-readable medium of claim 10, further comprising:

providing one or more actions to be taken for said one or more influencers.

12. The computer-readable medium of claim 10, wherein said determining said social network for each of said customers comprises:

defining a neighborhood for each of said customers;

determining a strength of relationships of each of said customers with members of said neighborhood of said customer; and

truncating said neighborhood for each of said customers by selecting k neighbors of each of said customers, wherein said k is a predetermined integer.

13. The computer-readable medium of claim 12, wherein said determining said social network for each of said customers further comprises:

recursively finding one or more neighborhoods for each of the remaining members in said neighborhood for a pre-determined number of times; and

defining said social network for each of said customers as the neighborhood that comprises said truncated neighborhood of said customer and the recursively found one or more neighborhoods.

14. The computer-readable medium of claim 12, wherein said truncating said neighborhood is performed by selecting a most important k neighbors using said strength of relationships.

15. The computer-readable medium of claim 10, further comprising:

implementing a model for predicting said measure of influence for each of said customers.

16. The computer-readable medium of claim 15, wherein said model is a statistical model.

17. The computer-readable medium of claim 16, wherein said statistical model comprises at least one of:

a linear regression model, a logistic regression model, a classification model or a neural networks model.

18. The computer-readable medium of claim 11, wherein said one or more actions comprises one or more directing marketing actions.

19. An apparatus for identifying one or more influencers, comprising:

means for obtaining a list of customers;

means for determining a social network for each of said customers;

means for selecting one or more attributes to be used for predicting a measure of influence for each of said customers; and

means for determining one or more influencers in said social network by using said one or more attributes.

20. The apparatus of claim 19, further comprising:

means for providing one or more actions to be taken for said one or more influencers.