DETERMINING WHETHER TO PROVIDE AN ADVERTISEMENT TO A USER OF A SOCIAL NETWORK

• US 20120066053A1
• Filed: 09/15/2010
• Published: 03/15/2012
• Est. Priority Date: 09/15/2010
• Status: Active Grant

• Current Assignee: R2 Solutions LLC (Acacia Research Corporation)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Agarwal, Deepak K.
• Granted Patent: US 8,478,697 B2
• Time in Patent Office: Days
• US Class Current: 705/14.41
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities
• CPC Class Codes: G06Q 30/0204 Market segmentation
• CPC Class Codes: G06Q 30/0242 Determining effectiveness of advertisements
• CPC Class Codes: G06Q 30/0254 based on statistics
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

Techniques are described herein for determining whether to provide an advertisement to a user of a social network. The determination is based on a click probability and a social network value for the user. The click probability indicates a likelihood of the user to select the advertisement if provided to the user via the social network. The social network value is based on a subscription probability of the user and further based on subscription probabilities of other users in the social network that are included in an affinity set of the user. Each subscription probability indicates a likelihood of a respective user to subscribe to a paid service with respect to the social network.

Claims

1. A method comprising:

determining a click probability for a first user of a social network using at least one processor, the click probability indicating a likelihood of the first user to select a first advertisement if the first advertisement is provided to the first user via the social network;

determining a plurality of subscription probabilities for a plurality of respective users of the social network, the plurality of users including the first user and second users that are included in an affinity set of the first user, each subscription probability indicating a likelihood of a respective user of the plurality of users to subscribe to a paid service with respect to the social network; and

determining a social network value for the first user based on the plurality of subscription probabilities; and

determining whether to provide the first advertisement to the first user based on the click probability and the social network value.

2. The method of claim 1, further comprising:

assigning a plurality of weights to the plurality of respective users;

wherein determining the social network value comprises;

determining the social network value based on the plurality of subscription probabilities and the plurality of respective weights.

3. The method of claim 2, wherein each weight that is assigned to a second user is based on an extent with which the first user communicates with that second user.

4. The method of claim 1, wherein determining whether to provide the first advertisement comprises:

combining the click probability and the social network value to provide a risk value that indicates a likelihood of the first advertisement to negatively impact an experience of the first user with respect to the social network; and

wherein the method further comprises;

if the risk value is less than a risk threshold, providing the first advertisement to the first user; and

if the risk value is greater than risk threshold, providing a second advertisement in lieu of the first advertisement to the first user.

5. The method of claim 1, wherein determining whether to provide the first advertisement to the first user comprises:

combining the click probability and the social network value to provide a risk value that indicates a likelihood of the first advertisement to negatively impact an experience of the first user with respect to the social network; and

wherein the method further comprises;

if the risk value is less than a risk threshold, providing the first advertisement to the first user; and

if the risk value is greater than the risk threshold, not providing the first advertisement to the first user.

6. The method of claim 1, wherein determining the click probability for the first user comprises:

applying a plurality of machine learned rules to a plurality of attributes of one or more of the first user, the first advertisement, or the social network to determine the click probability.

7. The method of claim 1, wherein determining the plurality of subscription probabilities comprises:

applying a plurality of machine learned rules to a plurality of attributes of each user of the plurality of users to determine the plurality of respective subscription probabilities.

8. The method of claim 1, wherein determining the social network value comprises:

assigning the plurality of subscription probabilities as a plurality of respective initial scores for the plurality of respective users; and

iteratively calculating an updated score for each user in the plurality of users based on the plurality of initial scores to determine the social network value for the first user.

9. The method of claim 8, wherein iteratively calculating the updated score for each user in the plurality of users is performed until the updated scores for the respective users substantially converge to respective fixed scores.

10. The method of claim 1, wherein determining whether to provide the first advertisement comprises:

determining that the first advertisement is to be provided to the first user in response to the click probability being greater than a first threshold and the social network value being less than a second threshold.

11. The method of claim 1, wherein determining whether to provide the first advertisement comprises:

determining that the first advertisement is not to be provided to the first user in response to the click probability being less than a threshold.

12. The method of claim 1, wherein determining whether to provide the first advertisement comprises:

determining that the first advertisement is not to be provided to the first user in response to the social network value being greater than a threshold.

13. A system comprising:

a click probability module configured to determine a click probability for a first user of a social network, the click probability indicating a likelihood of the first user to select a first advertisement if the first advertisement is provided to the user via the social network;

a subscription probability module configured to determine a plurality of subscription probabilities for a plurality of respective users of the social network, the plurality of users including the first user and second users that are included in an affinity set of the first user, each subscription probability indicating a likelihood of a respective user of the plurality of users to subscribe to a paid service with respect to the social network;

a network value module configured to determine a social network value for the first user based on the plurality of subscription probabilities; and

a provision determination module configured to determine whether to provide the first advertisement to the first user based on the click probability and the social network value.

14. The system of claim 13, further comprising:

an assignment module configured to assign a plurality of weights to the plurality of respective users;

wherein the network value module is configured to determine the social network value based on the plurality of subscription probabilities and the plurality of respective weights.

15. The system of claim 14, wherein each weight that is assigned to a second user is based on an extent with which the first user communicates with that second user.

16. The system of claim 13, wherein the provision determination module comprises:

a combination module configured to combine the click probability and the social network value to provide a risk value that indicates a likelihood of the first advertisement to negatively impact an experience of the first user with respect to the social network; and

a providing module configured to provide the first advertisement to the first user if the risk value is less than a risk threshold, the providing module further configured to not provide the first advertisement to the first user if the risk value is greater than the risk threshold.

17. The system of claim 13, wherein the click probability module is configured to apply a plurality of machine learned rules to a plurality of attributes of one or more of the first user, the first advertisement, or the social network to determine the click probability.

18. The system of claim 13, wherein the subscription probability module is configured to apply a plurality of machine learned rules to a plurality of attributes of each user of the plurality of users to determine the plurality of respective subscription probabilities.

19. The system of claim 13, wherein the network value module comprises:

an assignment module configured to assign the plurality of subscription probabilities as a plurality of respective initial scores for the plurality of respective users; and

an iterative calculation module configured to iteratively calculate an updated score for each user in the plurality of users based on the plurality of initial scores to determine the social network value for the first user.

20. A computer program product comprising a computer-readable medium having computer program logic recorded thereon for enabling a processor-based system to provide targeted advertising in a social networking computer system, comprising:

a first program logic module for enabling the processor-based system to determine a click probability for a first user of a social network, the click probability indicating a likelihood of the first user to select a first advertisement if the first advertisement is provided to the first user via the social network;

a second program logic module for enabling the processor-based system to determine a plurality of subscription probabilities for a plurality of respective users of the social network, the plurality of users including the first user and second users that are included in an affinity set of the first user, each subscription probability indicating a likelihood of a respective user of the plurality of users to subscribe to a paid service with respect to the social network;

a third program logic module for enabling the processor-based system to determine a social network value for the first user based on the plurality of subscription probabilities; and

a fourth program logic module for enabling the processor-based system to determine whether to provide the first advertisement to the first user based on the click probability and the social network value.