COMPUTER PROCESSES FOR IDENTIFYING RELATED ITEMS AND GENERATING PERSONALIZED ITEM RECOMMENDATIONS

• US 20080040239A1
• Filed: 08/20/2007
• Published: 02/14/2008
• Est. Priority Date: 09/18/1998
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Eric Benson, Gregory Linden, Jennifer Jacobi
• Inventors: Benson, Eric, Linden, Gregory, Jacobi, Jennifer
• Granted Patent: US 7,945,475 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 30/0253 During e-commerce, i.e. online transactions
• CPC Class Codes: G06Q 30/0254 based on statistics
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G06Q 30/0256 User search
• CPC Class Codes: G06Q 30/0271 Personalized advertisement
• CPC Class Codes: G06Q 30/0277 Online advertisement
• 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 30/0603 Catalogue ordering
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G06Q 30/0633 Lists, e.g. purchase orders, compilation or processing
• CPC Class Codes: G06Q 30/0641 Shopping interfaces
• CPC Class Codes: H04L 51/02 using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface

Abstract

A computer-implemented service analyzes purchase histories and/or other types of behavioral data of users on an aggregated basis to detect and quantify associations between particular items represented in an electronic catalog. The detected associations are stored in a mapping structure that maps items to related items, and is used to recommend items to users of the electronic catalog.

Claims

1. A computer-implemented method of selecting items to recommend to a user, the method comprising:

selecting a plurality of items associated with the user, including items selected from at least one of the following groups of items;

(a) items that have been purchased by the user, (b) items that have been explicitly rated by the user, (c) items in an electronic shopping cart of the user, (d) items the user has removed from said electronic shopping cart;

for each of the plurality of items, looking up a corresponding set of related items and associated data values, each data value representing a degree to which the related item is related to the respective item associated with the user;

generating a ranked set of said related items, such that a ranking of a related item in said ranked set is dependent upon (a) at least some of said data values, and (b) whether the related item appears in more than one of said sets of related items; and

selecting, from said ranked set of related items, a subset of related items to recommend to the user.

2. The method of claim 1, wherein the method is performed in real time in response to a request from the user for recommendations.

3. The method of claim 1, wherein said data values represent purchase-based relationships between items as assessed by analyzing purchase histories of a plurality of users.

4. The method of claim 1, further comprising generating said data values, at least in part, by analyzing purchase histories of a plurality of users in an off-line processing mode.

5. The method of claim 1, wherein generating the ranked set of related items comprises weighting some of said sets of related items more heavily than others, wherein weighting a set of related items relatively heavily increases a likelihood that items will be selected from that set of related items to recommend to the user.

6. The method of claim 5, wherein the method comprises, for a set of related items corresponding to an item explicitly rated by the user, weighting the set of related items by an amount that depends on the user'"'"'s explicit rating of said item.

7. The method of claim 5, wherein the method comprises, for a set of related items corresponding to an item purchased by the user, weighting the set of related items by an amount that depends on how recently the user purchased said item.

8. The method of claim 1, wherein selecting the plurality of items associated with the user comprises selecting one or more items from a purchase history of the user.

9. The method of claim 1, wherein selecting the plurality of items associated with the user comprises selecting one or more items from an item ratings profile of the user.

10. The method of claim 1, wherein the plurality of items associated with the user are selected exclusively from the electronic shopping cart of the user, and the method comprises outputting the top ranked subset of items for display on a web page that displays contents of the electronic shopping cart.

11. The method of claim 1, further comprising outputting a listing of the subset of related item to the user.

12. The method of claim 11, wherein the listing is provided on a web page that provides an option for the user to indicate ownership of particular related items and to request refined recommendations that reflect such indications of ownership.

13. The method of claim 11, further comprising providing an option for the user to view additional recommendations from said ranked set of related items.

14. A computer system configured to perform the method of claim 1.

15. A computer-readable medium having stored thereon executable code which embodies the method of claim 1.