BEHAVIOR-BASED SELECTION OF ITEMS TO PRESENT ON AFFILIATE SITES

• US 20090172551A1
• Filed: 12/28/2007
• Published: 07/02/2009
• Est. Priority Date: 12/28/2007
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Kane, Francis J., Hicks, Cory
• Granted Patent: US 8,271,878 B2
• Time in Patent Office: Days
• US Class Current: 715/733
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

A content provider system interacts with a network of web sites to provide behavior-based content to users. Operators of the web sites add widgets to selected web pages of their sites. The widgets, when executed on the computing devices of users who view the selected web pages, report user-generated events to the content provider system. The content provider system analyses the reported events to detect behavioral associations between particular web sites, web pages, products, and/or other types of items. The widgets may also retrieve and display behavior-based content that is based on these item-to-item behavioral associations. For example, when a user views a particular web page, a widget on that page may request and display descriptions of, and links to, other sites or pages that are (a) behaviorally related to the page being viewed or an item represented thereon, and/or (b) behaviorally related to the past browsing activities of the particular user.

Claims

1. A system, comprising:

an e-commerce web site that hosts an electronic catalog of items, said e-commerce web site configured to at least partially implement an affiliates program in which affiliates that operate affiliate web sites are paid commissions for user referrals that result in purchases from the electronic catalog;

an event recording system that records events descriptive of user actions performed across a plurality of web sites, including said e-commerce site and said affiliate web sites,

an association mining system that uses the recorded events to detect behavioral associations that associate particular web sites of said plurality of web sites, and/or particular pages of said web sites, with particular catalog items in the electronic catalog; and

a content generation system configured to use said behavioral associations to select particular catalog items to recommend to users on particular affiliate web sites, and to cause links to corresponding catalog pages of said electronic catalog to be displayed on pages of said affiliate web sites, said links being selectable by users to generate user referral events for which corresponding affiliates are capable of earning said commissions.

2. The system of claim 1, wherein the content generation system is configured to interact with widget code included in a web page of an affiliate web site to cause said web page to display said links when the page is viewed on a user computing device.

3. The system of claim 2, wherein the event recording system is configured to record item selection events reported via execution of said widget code.

4. The system of claim 1, wherein the content generation system is capable of using said behavioral associations to cause a web page of an affiliate web site to display recommendations of catalog items that are behaviorally related to the affiliate web site.

5. The system of claim 1, wherein the content generation system is capable of using said behavioral associations to cause a web page of an affiliate web site to display recommendations of catalog items that are behaviorally related to said web page.

6. The system of claim 1, wherein the content generation system is capable of using said behavioral associations, in combination with a prior event history of a target user, to generate personalized catalog-item recommendations to present to the target user on an affiliate web site.

7. The system of claim 1, wherein the content generation system is capable of using recorded event data descriptive of an event performed by a target user on a first web site, in combination with behavioral association data generated by the association mining system, to select one or more items to recommend to the target user on an affiliate web site that is separate from the first web site.

8. The system of claim 7, wherein said behavioral association data includes a mapping of web sites to related catalog items.

9. A computer-implemented method, comprising:

maintaining event data descriptive of at least (1) items selected by users from a target web site, and (2) accesses by said users to a plurality of web sites other than said target web site;

detecting a behavioral association between a first web site of said plurality of web sites and a particular item represented on the target web site, said behavioral association detected, at least in part, by performing an aggregated analysis of said event data over multiple users;

using said behavioral association to cause said item to be recommended to a user on an affiliate web site together with a link for accessing a corresponding page of the target web site, said affiliate web site being separate from the target web site; and

causing an operator of the affiliate web site to be compensated in response to the user selecting said link and completing a transaction on the target web site.

10. The method of claim 9, wherein the item is a catalog item represented in an electronic catalog of the target web site.

11. The method of claim 9, wherein the target web site is an e-commerce web site.

12. The method of claim 9, wherein the method comprises interacting over a network with widget code included in a web page of the affiliate web site to cause said catalog item to be recommended on said web page.

13. The method of claim 12, wherein maintaining said event data comprises recording events reported over a network via execution of said widget code.

14. The method of claim 9, wherein the first web site and the affiliate web site are the same web site.

15. The method of claim 9, wherein the first web site and the affiliate web site are separate, and the method comprises causing said item to be recommended to the user based on a prior access by the user to said first web site.

16. The method of claim 9, wherein the method comprises causing the affiliate web site to display items determined from said aggregated analysis to be behaviorally related to the affiliate web site.

17. The method of claim 9, wherein the method comprises causing the affiliate web site to display personalized catalog-item recommendations to the user.

18. A content provider system programmed and configured to perform the method of claim 9.