System for obtaining recommendations from multiple recommenders

• US 7,991,650 B2
• Filed: 08/12/2008
• Issued: 08/02/2011
• Est. Priority Date: 08/12/2008
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Kane, Francis J. Jr.
• Primary Examiner(s): Smith; Jeffrey A
• Assistant Examiner(s): Zukanovich; Brandy A
• Application Number:
  US12/190,501
• Publication Number:
  US 20100042460A1
• Time in Patent Office: 1,085 Days
• Field of Search: 705/26, 705/26.1, 705/26.7, 705/27
• US Class Current: 705/26.7
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0273 Determination of fees for advertising
• CPC Class Codes: G06Q 30/04 Billing or invoicing
• CPC Class Codes: G06Q 30/0603 Catalogue ordering
• CPC Class Codes: G06Q 30/0631 Item recommendations

Abstract

A personalization network service enables developers to develop recommenders that can be made available to content site operators for providing recommendations to end users. The personalization network service may also be capable of optimizing the use and selection of the recommenders for different end users, groups or segments of end users, content sites, and the like.

Claims

1. A system for providing recommendations to content sites, the system comprising:

a network service interface operative to;

receive a first request from a content site to store event data descriptive of user-generated events, the event data comprising identifiers of particular items and particular users to which the events correspond, the first request being received over a computer network;

receive a second request from the content site for item recommendations, the second request being received over the computer network;

an event data repository operative to store the event data received from the content site, the event data repository comprising physical computer storage;

a recommendations service operative to, in response to the second request, cause a plurality of external recommendation algorithms to provide recommendations responsive to the second request, the plurality of external recommendation algorithms being developed by recommender providers; and

a billing module comprising computer hardware, the billing module operative to cause an operator of the content site to be charged fees for obtaining recommendations from the plurality of external recommenders, and operative to cause at least a portion of the fees to be provided to the recommender providers such that monetary amounts paid to a recommender provider are dependent upon a level of performance of one or more recommendation algorithms provided by the recommender provider.

2. The system of claim 1, wherein the billing module is further operative to measure the performance of the one or more recommenders based at least partly on the event data.

3. The system of claim 1, wherein the user-generated events comprise one or more of user selections of particular recommended items and user purchases of particular recommended items.

4. The system of claim 1, wherein the billing module is further operative to measure the performance of the one or more recommenders based at least partly on recommendation requests served by the one or more recommenders.

5. The system of claim 1, wherein the computer hardware comprises a plurality of computing devices.

6. A computer-implemented method of compensating recommender providers, the method comprising:

invoking one or more recommendation algorithms to provide recommendations for a content site over a network for presentation to end users;

causing the content site to be charged a fee related to a user-generated event in response to determining that the user-generated event is attributable to a recommendation developed by the one or more recommendation algorithms; and

in response to said determination, causing at least a portion of the fee to be distributed to one or more developers of the one or more recommendation algorithms;

wherein at least said causing is performed by computer hardware.

7. The method of claim 6, wherein the determination that the user-generated event is attributable to the recommendation is based, at least in part, on a value of a timeframe between the recommendation and the user-generated event.

8. The method of claim 6, wherein the determination that the user-generated event is attributable to the recommendation is based, at least in part, on a number of mouse clicks between the recommendation and the user-generated event.

9. The method of claim 6, wherein the distribution of the at least a portion of the fee is based at least in part on weights applied to the one or more recommenders.

10. The method of claim 9, wherein the weights are generated based at least in part on past performance of the one or more recommenders.

11. The method of claim 9, wherein the weights are selected from a group consisting of user-specific weights, segment-specific weights, site-specific weights, global weights, and default weights.

12. The method of claim 6, wherein the distribution of the at least a portion of the fee is based at least in part on a number of events reported by the content site and attributed at least in part to the one or more recommenders.

13. The method of claim 12, wherein the events comprise one or more of user purchases of recommended items and user selections of recommended items.

14. The method of claim 6, wherein the distribution of the at least a portion of the fee is based at least in part on a number of recommendation requests served by the one or more recommenders.

15. The method of claim 6, wherein causing at least a portion of the fee to be distributed to one or more providers of the one or more recommenders comprises crediting one or more accounts of the one or more providers.