UNIFIED AUCTION MODEL FOR SUGGESTING RECOMMENDATION UNITS AND AD UNITS

• US 20140019233A1
• Filed: 07/13/2012
• Published: 01/16/2014
• Est. Priority Date: 07/13/2012
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: David Ye
• Inventors: Goder, Andrey, Shi, Yanxin, Hegeman, John, Ye, David
• Granted Patent: US 10,572,906 B2
• Time in Patent Office: Days
• US Class Current: 705/14.46
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0273 Determination of fees for advertising
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

A social networking system presents advertisements and recommendation units to its users. The recommendation units suggest actions for the users to increase their engagement with the social networking system or otherwise interact with other users, while the social networking system receives revenue from advertisers for displaying advertisements based on bid values associated with the advertisements. The social networking system determines values for the advertisements and for the recommendation units, where the values are measured in a comparable fashion. This allows the system to rank and select the advertisements and recommendation units together in a unified auction model. For example, the social networking system uses a pacing value to determine values of recommendation units having a common unit of measurement with expected values of advertisements to the social networking system.

Claims

1. A computer-implemented method comprising:

receiving a request for content from a viewing user of a social networking system;

retrieving a plurality of candidate advertisements for the viewing user, each candidate advertisement associated with a bid amount;

computing an expected value for each candidate advertisement based on the bid amount for the candidate advertisement;

receiving a plurality of candidate recommendation units for the viewing user, each candidate recommendation unit including a recommendation that the viewing user perform an action in the social networking system identified by the recommendation unit;

receiving a score for each candidate recommendation unit, where the score is based on a value to the social networking system of the viewing user performing the recommended action identified by the candidate recommendation unit;

converting the score for each candidate recommendation unit to a recommendation value, the recommendation value for each candidate recommendation unit having a common unit of measurement as the expected values associated with the candidate advertisements;

ranking the candidate advertisements and the candidate recommendation units together using the expected values of the candidate advertisements and the recommendation values of the candidate recommendation units;

selecting content for presentation to the viewing user based on the ranking, the content including a set including one or more candidate advertisements and one or more recommendation units; and

sending the selected content for display to the viewing user.

2. The computer-implemented method of claim 1, wherein a selected candidate advertisement has a maximum expected value.

3. The computer-implemented method of claim 1 wherein a selected recommendation unit has a maximum recommendation value.

4. The computer-implemented method of claim 1, wherein the score is based on at least one of the group consisting of:

prior interaction with recommendation units by the viewing user, other users to whom the viewing user is connected, and a probability of the viewing user interacting with the candidate recommendation unit.

5. The computer-implemented method of claim 1, wherein converting the score for each candidate recommendation unit to a recommendation value comprises:

applying a pacing value to the score, the pacing value specifying a relationship between the score and a unit of measurement for the expected value.

6. The computer-implemented method of claim 5, wherein the pacing value is based on a percentage of overall revenue to the social networking system received from presentation of advertisements.

7. The computer-implemented method of claim 1, wherein a candidate recommendation unit includes at least one of the group consisting of:

content identifying another user of the social network for the viewing user to connect to, content identifying an event for the viewing user to attend, content identifying an application, and content identifying a group.

8. The computer-implemented method of claim 1, wherein the common unit of measurement comprises a monetary value.

9. A computer-implemented method comprising:

receiving a request for content from a viewing user of a social networking system;

retrieving a plurality of candidate advertisements for the viewing user, each candidate advertisement associated with a bid amount;

computing an expected value for each candidate advertisement based on the bid amount for the candidate advertisement, the expected value having a first unit of measurement;

receiving a plurality of candidate recommendation units for the viewing user, each candidate recommendation unit including a recommendation that the viewing user perform an action in the social networking system identified by the recommendation unit;

receiving a score for each candidate recommendation unit, where the score is based on a value to the social networking system of the viewing user performing the recommended action identified by the candidate recommendation unit, the score having a second unit of measurement;

determining a common unit of measurement for the scores and the expected values;

converting the scores to transformed scores having the common unit of measurement and the expected values to transformed expected values having the common unit of measurement;

ranking the candidate advertisements and the candidate recommendation units together according to their transformed scores;

selecting content for presentation to the viewing user based on the ranking, the content including a set of at least one candidate advertisement and at least one recommendation unit; and

sending the selected content for display to the viewing user.

10. The computer-implemented method of claim 9, wherein determining the common unit of measurement for the scores and the expected values comprises:

selecting the first unit of measurement as the common unit of measurement.

11. The computer-implemented method of claim 10, wherein converting the scores to transformed scores having the common unit of measurement and the expected values to transformed expected values having the common unit of measurement comprises:

converting the score for each candidate recommendation unit to a recommendation value, the recommendation value for each candidate recommendation unit having the first unit of measurement.

12. The computer-implemented method of claim 11, wherein converting the score for each candidate recommendation unit to a recommendation value comprises:

applying a pacing value to the score, the pacing value specifying a conversion factor from the second value to the first value.

13. The computer-implemented method of claim 9, wherein determining the common unit of measurement for the scores and the expected values comprises:

selecting the second unit of measurement as the common unit of measurement.

14. The computer-implemented method of claim 13, wherein converting the scores to transformed scores having the common unit of measurement and the expected values to transformed expected values having the common unit of measurement comprises:

converting the expected value for each candidate advertisement to an advertisement score, the advertisement score for each candidate recommendation unit having the second unit of measurement.

15. The computer-implemented method of claim 9, wherein the common unit of measurement for the scores and the expected values comprise a monetary value.

16. The computer-implemented method of claim 9, wherein selecting content for presentation to the viewing user based on the ranking, the content including the set of at least one candidate advertisement and at least one recommendation unit comprises:

selecting at least one advertisement based on the ranking; and

selecting at least one recommendation unit based on the ranking

17. The computer-implemented method of claim 9, wherein selecting content for presentation to the viewing user based on the ranking, the content including the set of at least one candidate advertisement and at least one recommendation unit comprises:

applying one or more rules to the ranking, the one or more rules identifying a number of candidate advertisements or a number of recommendation units in the set.

18. A computer-implemented method comprising:

receiving a request for content from a viewing user of a social networking system, the content including a plurality of slots;

retrieving a plurality of candidate advertisements for the viewing user, each candidate advertisement associated with a bid amount;

computing an expected value for each candidate advertisement based on the bid amount for the candidate advertisement;

receiving a plurality of candidate recommendation units for the viewing user, each candidate recommendation unit including a recommendation that the viewing user perform an action in the social networking system identified by the recommendation unit;

receiving a score for each candidate recommendation unit, where the score is based on a value to the social networking system of the viewing user performing the recommended action identified by the candidate recommendation unit;

converting the score for each candidate recommendation unit to a recommendation value, the recommendation value for each candidate recommendation unit having a common unit of measurement as the expected values associated with the candidate advertisements;

ranking the candidate advertisements and the candidate recommendation units together, the candidate advertisements ranked according to their expected values and the candidate recommendation units ranked according to their recommendation values;

selecting content for inclusion in each of the plurality of slots based on the ranking, at least one slot including a candidate advertisement and at least one slot including a candidate recommendation unit; and

sending the selected content for display to the viewing user.

19. The computer-implemented method of claim 18, wherein selecting content for inclusion in each of the plurality of slots based on the ranking, at least one slot including a candidate advertisement and at least one slot including a candidate recommendation unit comprises:

selecting a slot;

identifying a maximum of the expected values and the recommendation values; and

selecting content associated with the maximum of the expected values and the recommendation values for inclusion in the selected slot.

20. The computer-implemented method of claim 18, wherein selecting content for inclusion in each of the plurality of slots based on the ranking, at least one slot including a candidate advertisement and at least one slot including a candidate recommendation unit comprises:

determining an order in which the plurality of slots are displayed based on an expected value or recommendation value associated with content included in each of the slots.

21. The computer-implemented method of claim 18, wherein the score is based on at least one of the group consisting of:

prior interaction with recommendation units by the viewing user, other users to whom the viewing user is connected, and a probability of the viewing user interacting with the candidate recommendation unit.