METHOD, MEDIUM AND SYSTEM FOR DETERMINING WHETHER A TARGET ITEM IS RELATED TO A CANDIDATE AFFINITY ITEM

• US 20100121777A1
• Filed: 11/10/2009
• Published: 05/13/2010
• Est. Priority Date: 05/14/2007
• Status: Active Grant

• Current Assignee: Acoustic, L.P.
• Original Assignee: Coremetrics Incorporated (International Business Machines Corporation)
• Inventors: Puttaswamy, Hemanth, Niemann, Mike, McGonigal, Charles, Guntumadugu, Saritha, Salsbury, Russell, Ogireddy, Srinivasa
• Granted Patent: US 10,304,113 B2
• Time in Patent Office: Days
• US Class Current: 705/347
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0282 Rating or review of business operators or products
• CPC Class Codes: G06Q 30/0631 Item recommendations

Abstract

Recommendations for purchase are made based on customer behavior across multiple sessions. Correlations used for recommendations include: buy-to-buy (cross-session), view-to-view (same-session), view-to-buy (same-session), and abandon-to-buy (same-session) actions. A preview display allows a merchant to adjust recommendation algorithm weightings to achieve a desired result. A closed-loop system is provided with real-time feedback. The recommendations can be based on various segments of other users, including users of the same search engine.

Claims

1-17. -17. (canceled)

18. A method comprising:

collecting data corresponding to monitored actions of a user of a web site, the monitored actions collected over a plurality of browsing sessions;

identifying, with a server computer, at least one affinity product related to a target product, the identifying based on the monitored actions and a weighted formula;

displaying, with the server computer, a preview of the at least one affinity product;

modifying at least one weight of the weighted formula; and

displaying, with the server computer, an updated preview showing any change in the at least one affinity product due to the modifying.

19. The method of claim 18 further wherein said at least one affinity product comprises a plurality of affinity products.

20. The method of claim 19 further comprising:

receiving a selection of at least one product to exclude from identification as said at least one affinity product.

21. The method of claim 19 wherein said weighted formula provides at least two correlations of a browsing or buying action of a first product by a first user with browsing, abandoning or buying actions of a group of users who also browsed or bought said first product.

22. The method of claim 19 wherein said monitored actions include keywords, and said at least one affinity product is a product on which action was taken by a group of users who used the same keyword.

23. The method of claim 19 further comprising:

receiving a selection indicating a number of affinity products to be identified.

24. The method of claim 19 further comprising:

displaying a conversion measure for the at least one affinity product in the displayed preview.

25. The method of claim 18 further comprising:

exporting a list of the at least one affinity product to a merchant'"'"'s web site for use in displaying the at least one affinity product when the target product is displayed.

26. A method comprising:

collecting data corresponding to monitored actions of a user of a web site, the monitored actions collected over a plurality of browsing sessions;

providing a formula for identifying affinity products based on said monitored actions;

tracking said monitored actions for an identified segment of users; and

selecting, with a server computer, at least one affinity product using said formula and said monitored actions of said segment of users.

27. The method of claim 26 wherein said segment is selected from the group of segments comprising product market segment, time related segment, user characteristic segment, geographical segment and browsing action segment.

28. The method of claim 26 wherein said at least one selected affinity product is selected based on a relation to a target product.

29. The method of claim 26 further comprising:

excluding at least one affinity product from display if it is contained on a list of excluded affinity products.

30. The method of claim 26 wherein the collected data is collected from a plurality of web sites operated by a plurality of web site operators.

31. The method of claim 30 wherein said formula identifies said affinity products based on cross session and cross web site monitored actions.

32. The method of claim 26, wherein said formula identifies said affinity products based in part on a conversion measure of affinity products.

33. The method of claim 28, further comprising:

exporting said selected affinity product for display on a results page of a search engine; and

displaying said selected affinity product when a search performed on the search engine results in the target product.

34. A method comprising:

collecting data corresponding to monitored keywords;

providing a formula for identifying affinity products based on said monitored keywords;

tracking said monitored keywords and affinity products for an identified segment of users; and

selecting, with a server computer, at least one affinity product using said formula and said monitored keywords of said segment of users.

35. The method of claim 34 wherein said identified segment of users are users of the same search engine.

36. The method of claim 34 wherein said selected at least one affinity product is selected based at least in part on a relation to a target product.

37. The method of claim 34 wherein said selected at least on affinity product is selected based at least in part on a conversion measure of the identified affinity products.