EXTRAPOLATION OF BEHAVIOR-BASED ASSOCIATIONS TO BEHAVIOR-DEFICIENT ITEMS

• US 20080004989A1
• Filed: 06/16/2006
• Published: 01/03/2008
• Est. Priority Date: 06/16/2006
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Yi, Jin Y.
• Granted Patent: US 8,032,425 B2
• Time in Patent Office: Days
• US Class Current: 705/27
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0601 Electronic shopping [e-shopping]
• CPC Class Codes: G06Q 30/0629 for generating comparisons
• CPC Class Codes: G06Q 30/0631 Item recommendations

Abstract

Behavior-based associations are extrapolated to items for which the quantity of collected user activity data is insufficient to create meaningful or reliable behavior-based associations (“behavior-deficient” items). The behavior-based associations are extrapolated based on content-based associations, or another type of “substitutability” association, between the behavior-deficient items and other items. The items can be any type of item for which user behaviors (e.g., purchases, accesses, downloads, etc.) can be monitored and analyzed to detect behavior-based associations, and for which item content or other available information can be used to assess item substitutability. For example, the items can be products represented in an electronic catalog, web pages or other documents accessible on a network, or web sites.

Claims

1. A computer-implemented method of detecting associations between items represented in an electronic catalog, the method comprising:

maintaining item selection histories of each of a plurality of users of the electronic catalog, said item selection histories identifying particular items selected by particular users;

detecting a behavior-based association between two items represented in the electronic catalog, item A and item B, at least in part by programmatically analyzing said item selection histories;

detecting a substitutability association between item A and an additional item, item C, represented in the electronic catalog; and

programmatically using the detected behavior-based association between items A and B, in combination with the detected substitutability association between item A and item C, to create, in computer storage, an association between item B and item C.

2. The method of claim 1, wherein the method comprises:

generating a first data value that represents a strength of the behavior-based association between items A and B;

generating a second data value that represents a strength of the substitutability association between items A and C; and

generating a third data value that represents a strength of the association between items B and C, such that the third data value is dependent on the first and second data values.

3. The method of claim 1, wherein the substitutability association is detected, at least in part, by analyzing attributes of items A and C.

4. The method of claim 1, wherein the substitutability association is detected, at least in part, by analyzing item viewing histories of users of the electronic catalog.

5. The method of claim 4, wherein the behavior-based association is detected based on purchase histories of users.

6. The method of claim 1, wherein item C is a behavior-deficient item.

7. The method of claim 6, further comprising phasing out or terminating the created association between items B and C in response to the collection of sufficient item selection history data for creating behavioral-based associations between item C and other items.

8. The method of claim 1, wherein item B and item C are not substitutable.

9. The method of claim 1, wherein the association created between items B and C is a directional association from item C to item B.

10. A computer-readable storage medium have stored thereon a computer program which comprises executable instructions that, when executed, cause a computer system to perform the method of claim 1.

11. A computer system for detecting associations between items represented in an electronic catalog of items, the system comprising:

an item data repository that stores catalog descriptions of items represented in the electronic catalog;

a substitutability association mining component that detects substitutability associations between particular items represented in the electronic catalog, at least in part, by analyzing said catalog descriptions;

a data repository that stores item selection histories of a plurality of users of the electronic catalog, said item selection histories identifying particular items selected by particular users;

a behavior-based association mining component that detects behavior-based associations between particular items, at least in part, by analyzing the item selection histories of the plurality of users; and

an extrapolation component that uses the substitutability associations in combination with the behavior-based associations to detect additional associations between items.

12. The system of claim 11, wherein the extrapolation component is capable of using a behavior-based association between a first item and a second item, in combination with a substitutability association between the first item and a third item, to create an extrapolated behavioral association between the second and third items.

13. The system of claim 11, wherein the extrapolation component is capable of creating an association between two items between for which no behavior-based association and no content-based association exists.

14. The system of claim 11, wherein the substitutability association mining component additionally uses item viewing histories of users to detect said substitutability associations.

15. The system of claim 11, wherein the item selection histories are item purchase histories.

16. A computer-implemented method, comprising:

generating a first data value that represents a strength of a behavior-based association between a first item and either (a) a second item, or (b) a search query, said behavior-based association based on collected user activity data reflective of actions of a plurality of users;

generating a second data value that represents a content-based association between the first item and a behavior-deficient item, said content-based association based on content of, or descriptive of, the first item and the behavior-deficient item; and

generating a third data value that represents a strength of an association between the behavior-deficient item and either the second item or the search query, said third data value being dependent upon the first data value and the second data value.

17. The method of claim 16, wherein the first data value represents a strength of a behavior-based association between the first and second items, and the third data value represents a strength of an association between the behavior-deficient item and the second item.

18. The method of claim 17, further comprising using the third data value to determine whether to display the second item on an item detail page for the behavior-deficient item.

19. The method of claim 18, wherein the first and second items are products represented in an electronic catalog.

20. The method of claim 16, wherein the first data value represents a strength of a behavior-based association between the first item and the search query, and the third data value represents a strength of an association between the behavior-deficient item and the search query.

21. The method of claim 20, further comprising using the third data value to determine a display rank of the behavior-deficient item in a search result listing for the search query.

22. The method of claim 20, further comprising using the third data value to cause the behavior-deficient item to be added to a search result set for the search query.

23. The method of claim 16, further comprising using the third data value to increase an exposure of the behavior-deficient item to users.

24. The method of claim 16, wherein the third data value is additionally based on data reflective of how frequently the first item and the behavior-deficient item are viewed in a common browsing session.

25. A computer-readable storage medium have stored thereon a computer program which comprises executable instructions that, when executed, cause a computer system to perform the method of claim 16.

26. A computer system, comprising:

a behavior-based association mining component configured to analyze collected user activity data reflective of actions of a plurality of users, and based thereon, to detect at least one of the following types of behavior-based associations;

(a) behavior-based associations between particular items, (b) behavior-based associations between particular items and search queries;

a content-based association mining component configured to analyze item content, and based thereon, to detect content-based associations between particular behavior-deficient items and other items; and

an extrapolation component configured to create new associations by extrapolating selected behavior-based associations detected by the behavior-based association mining component to the behavior-deficient items based, at least in part, on said content-based associations between particular behavior-deficient items and other items.

27. The system of claim 26, wherein the behavior-based association mining component is configured to detect a behavior-based association between first and second items, and the extrapolation component is configured to extrapolate said behavior-based association to a behavior-deficient item based on a content-based association between the behavior-deficient item and the first item, to thereby create a new association between the behavior-deficient item and the second item.

28. The system of claim 27, further comprising a page generator component that uses the new association to select the second item for display on an item detail page for the behavior-deficient item.

29. The system of claim 26, wherein the behavior-based association mining component is configured to a detect behavior-based association between a search query and a first item, and the extrapolation component is configured to extrapolate said behavior-based association to a behavior-deficient item based on a content-based association between the behavior-deficient item and the first item, to thereby create a new association between the search query and the behavior-deficient item.

30. The system of claim 29, further comprising a search engine system configured to use the new association between the search query and the behavior-deficient item to increase a search result display rank of the behavior-deficient item.

31. The system of claim 29, further comprising a search engine system configured to use the new association between the search query and the behavior-deficient item to cause the behavior-deficient item to be added to a search results set for the search query.

32. The system of claim 26, wherein the extrapolation component additionally extrapolates the behavior-based associations to behavior-deficient items based on item-viewing-history based substitutability associations between the behavior-deficient items and other items.

33. The system of claim 26, wherein:

the behavior-based association mining component is configured to generate data values representing strengths of said behavior-based associations;

the content-based association mining component is configured to generate data values representing strengths of said content-based associations; and

the extrapolation component is configured to use the data values generated by the behavior-based association mining component, in combination with the data values generated by the content-based association mining component, to extrapolate behavior-based associations to the behavior-deficient items.