Identifying and providing targeted content to users having common interests

• US 7,827,055 B1
• Filed: 06/07/2001
• Issued: 11/02/2010
• Est. Priority Date: 06/07/2001
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon.com, Inc.
• Inventors: McDaniel, Michael, Snodgrass, Ryan J.
• Primary Examiner(s): VAN BRAMER, JOHN W
• Application Number:
  US09/876,611
• Time in Patent Office: 3,435 Days
• Field of Search: 705/14
• US Class Current: 705/14.26
• 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

A computer process is disclosed for selecting items to present or recommend to users based on the referring sites accessed by such users. The process includes tracking referrals of users from referring sites to a target site, and recording the item selections of the referred users from an electronic catalog of the target site. The process may also include analyzing the recorded item selections of the users to identify, for a particular subset of the referring sites, a set of items that correspond to group preferences of users referred to the target site by the subset of referring sites. These identified items may thereafter be presented to users who access a site that is a member of the subset of referring sites.

Claims

1. A computer-implemented method, comprising:

tracking referrals of users from each of a plurality of referring web sites to a target web site that hosts an electronic catalog of items, said referrals resulting from user selections of links provided on the referring web sites;

identifying a group of users referred to the target web site by a selected subset of said plurality of referring web sites, said group of users comprising a plurality of users, and representing a subpopulation of a general user population of the target web site;

collecting user activity data reflective of preferences of particular users for particular items represented in the electronic catalog of items, said user activity data encompassing actions of both members and non-members of said group of users;

identifying a set of items that correspond to group preferences of said group of users, wherein the set of items is identified based on the collected user activity data of both the members and the non-members of said group of users; and

causing the set of items to be displayed (a) on the target web site to users who are referred thereto from a referring web site in said subset of referring web sites, and/or (b) on a referring web site in said subset of referring web sites.

2. The method of claim 1, wherein identifying the set of items comprises programmatically analyzing the collected user activity data of the members and non-members of the group to identify items that are significantly more popular among the group of users than in the general user population.

3. The method of claim 1, wherein identifying the set of items comprises programmatically analyzing the collected user activity data of the members and non-members of the group to identify items for which the group'"'"'s preferences are significantly greater than the general user population'"'"'s preferences.

4. The method of claim 1, wherein the user activity data comprises data descriptive of item purchases made by users.

5. The method of claim 1, wherein the user activity data comprises user-specific item viewing histories.

6. The method of claim 1, wherein the method comprises causing the set of items to be displayed on the target web site to users who are referred thereto from a referring web site in said subset of referring web sites.

7. The method of claim 1, wherein the method comprises causing the set of items to be displayed on a page that is initially presented to a user when the user is referred to the target web site from a referring web site in said subset of referring web sites.

8. The method of claim 7, wherein the page is a product detail page of the target web site.

9. The method of claim 1, wherein the method comprises causing the set of items to be displayed on a referring web site in said subset of referring web sites.

10. The method of claim 1, wherein the set of items is caused to be displayed together with a community name associated with said group of users.

11. The method of claim 1, wherein the subset of referring web sites consists of a single referring web site.

12. The method of claim 1, wherein the subset of referring web sites includes one or more associate web sites.

13. The method of claim 1, wherein the subset of referring web sites consists of a plurality of referring web sites that are associated with a common topic.

14. The method of claim 1, wherein the items include books that are available for purchase from the target web site.

15. The method of claim 1, further comprising repeating the method for each of a plurality of additional groups of users, each group corresponding to a different respective subset of the plurality of referring web sites, and corresponding to a different respective topic.

16. A computer system, comprising:

a referral tracking system that tracks referrals of users from a plurality of referring sites to a target site, said target site including an electronic catalog of items;

a data repository that stores user activity data reflective of user actions performed with respect to items represented in the electronic catalog, said user activity data reflective of user preferences for particular items; and

a recommendations service configured to (a) identify a group of users that have been referred to the target site by a selected subset of the referring sites, (b) analyze the user activity data of both members and non-members of said group to identify a set of items that are significantly more popular in the group than in a general user population of the target site, and (c) cause the identified set of items to be suggested to users that visit a referring site in said subset of referring sites.

17. The computer system of claim 16, wherein the user activity data identifies item purchases made by particular users.

18. The computer system of claim 16, wherein the user activity data comprises user-specific item viewing histories.

19. The computer system of claim 16, wherein the recommendations service is configured to cause the set of items to be displayed on the target site to users who are referred thereto from a referring site in said subset of referring sites.

20. The computer system of claim 16, wherein the recommendations service is configured to cause the set of items to be displayed on a page that is initially presented to a user when the user is referred to the target site from a referring site in said subset of referring sites.

21. The computer system of claim 20, wherein the page is a product detail page of the target site.

22. The computer system of claim 16, wherein the recommendations service is configured to cause the set of items to be displayed on a referring site of said subset of referring sites.

23. The computer system of claim 16, wherein the recommendations service is configured to cause the set of items to be displayed together with a community name associated with said group of users.

24. The computer system of claim 16, wherein the subset of referring sites consists of a single referring site.

25. The computer system of claim 16, wherein the subset of referring sites includes a plurality of referring sites associated with a common area of interest.

26. The computer system of claim 16, wherein the subset of referring sites includes one or more associate sites.

27. The computer system of claim 16, wherein the items include books that are available for purchase from the target site.

28. The computer system of claim 16, wherein the recommendations service is configured to identify items that are unusually popular in each of a plurality of groups, each group corresponding to a different respective subset of the referring sites, and corresponding to a different area of user interest.