REFERRING-SITE BASED RECOMMENDATIONS

• US 20100161400A1
• Filed: 02/26/2010
• Published: 06/24/2010
• Est. Priority Date: 06/07/2001
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Michael Mcdaniel, Ryan J. Snodgrass
• Inventors: McDaniel, Michael, Snodgrass, Ryan J.
• Granted Patent: US 8,285,589 B2
• Time in Patent Office: Days
• US Class Current: 705/14.160
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0214 Referral reward systems
• CPC Class Codes: G06Q 30/0225 Avoiding frauds
• CPC Class Codes: G06Q 30/0282 Rating or review of business operators or products
• CPC Class Codes: G06Q 30/0601 Electronic shopping [e-shopping]
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

Systems and methods are disclosed for providing community-specific content to customers of a merchant'"'"'s web site. In one embodiment, customers who are electronically referred to the merchant'"'"'s web site from an affiliate web site, or from one of a group of related affiliate web sites, are automatically assigned to the same community. For example, all customers who enter the merchant'"'"'s web site from links on golf-related affiliate web sites may be assigned to the community “golf.” Customers may also join or be assigned to communities using other methods. Purchase histories and/or other activity data of the merchant'"'"'s customers is analyzed periodically to identify specific products or other items that are currently “popular” within the community (e.g., best selling), based upon predefined criteria. This information is provided to members of the community, and possibly to other customers, on the merchant'"'"'s web site and/or on the web sites of the corresponding affiliates.

Claims

1. A method for selecting items to recommend to users, the method comprising:

tracking referrals of users from each of a plurality of referring sites to a target site, said referrals resulting from user selections of links provided on the referring sites;

collecting user activity data regarding item-specific user actions performed on the target site, said item-specific user actions reflective of user preferences for particular items represented on the target site; and

selecting, by execution of code by a computer system, a subset of said items to recommend to users of a first referring site of said plurality of referring sites, wherein selecting the subset of items comprises analyzing the collected user activity data, in conjunction with data regarding the tracked referrals, to identify items that are more popular among users referred from the first referring site than among a general user population of the target site.

2. The method of claim 1, wherein the items are products represented in an electronic product catalog hosted by the target site.

3. The method of claim 2, wherein the user activity data comprises data representing user purchases of particular products represented in the electronic catalog.

4. The method of claim 1, wherein the items are electronic content items that are retrievable from the target site.

5. The method of claim 1, wherein the referring sites are affiliate sites that participate in an affiliate marketing program of the target site.

6. The method of claim 5, wherein the method comprises assigning at least some of the users of the target site to affiliate-based communities based on the affiliate sites that referred such users to the target site, and identifying, for each affiliate-based community, items that are significantly more popular among members of the respective affiliate-based community than among a general user population of the target site.

7. The method of claim 1, further comprising causing the subset of items to be recommended to an unknown or unrecognized user of the first referring site.

8. The method of claim 1, further comprising, when an unknown or unrecognized user is referred from the first referring site to the target site, causing the subset of items to be recommended to the unknown or unrecognized user.

9. A system for selecting items to recommend to users, the system comprising:

a computer data repository that stores referral data identifying, for each of a plurality of users of a target site, which of a plurality of referring sites referred the respective user to the target site; and

a computer data repository that stores user activity data identifying item-specific actions performed by users on the target site, said item-specific user actions reflective of user preferences for particular items represented on the target site; and

a computer system programmed to select a subset of said items to recommend to users of a first referring site of said plurality of referring sites, said computer system programmed to select the subset of items at least partly by analyzing the user activity data, in conjunction with the referral data, to identify items that are more popular among users referred from the first referring site than among a general user population of the target site.

10. The system of claim 9, wherein the items are products represented in an electronic catalog hosted by the target site.

11. The system of claim 10, wherein the user activity data comprises data representing user purchases of particular products represented in the electronic catalog.

12. The system of claim 9, wherein the items are electronic content items that are viewable on the target site.

13. The system of claim 9, wherein the referring sites are affiliate sites that participate in an affiliate marketing program associated with the target site.

14. The system of claim 13, wherein the computer system is programmed to assign users of the target site to communities based on the affiliate sites that referred such users to the target site, and to identify, for each community, items that more popular among members of the respective community than among a general user population of the target site.

15. The system of claim 9, wherein the computer system is programmed to cause the subset of items to be recommended to an unknown or unrecognized user of the first referring site.

16. The system of claim 15, wherein the computer system is programmed to cause the subset of items to be recommended to the unknown or unrecognized user when the unknown or unrecognized user is referred from the first referring site to the target site.

17. A computer implemented method, comprising:

receiving, at a server of a target site, a page request from a computing device of an unknown or unrecognized user, said page request resulting from selection by the user of a referral link on a referring site, said page request including an identifier of the referring site; and

selecting a set of items to present to the unknown or unrecognized user in response to the page request, said set of items selected by the server based on the identifier of the referring site, said set of items consisting of items that are more popular among users referred from the referring site than among a general user population of the target site, as determined based on a programmatic analysis of actions performed on the target site by users referred from the referring site and by users not referred from the target site.

18. The method of claim 17, wherein the referring site is an affiliate site that participates in an affiliates program of the target site.

19. The method of claim 18, wherein the items are products represented in an electronic catalog of the target site.

20. The method of claim 18, further comprising, by execution of code by a computer system, performing said programmatic analysis of actions performed on the target site to identify said set of items.