Method, medium, and system for determining whether a target item is related to a candidate affinity item
First Claim
Patent Images
1. A method of identifying related items, comprising:
- monitoring actions performed on a plurality of items by a plurality of users across a plurality of websites;
selecting from the plurality of items, a target item;
selecting, from the plurality of items, a candidate affinity item;
determining whether the candidate affinity item is related to the target item using the following analysis;
calculating, from the plurality of users, across a plurality of websites;
a first amount, representing how many users viewed the target item and the candidate affinity item in the same browsing session;
a second amount, representing how many users viewed the target item and bought the candidate affinity item in the same browsing session;
a third amount, representing how many users bought the target item and the candidate affinity item in different browsing sessions; and
a fourth amount, representing how many users did not buy the target item after adding it to their shopping cart but did buy the candidate affinity item in the same browsing session;
receiving, for each of the four amounts, a corresponding weighting factor;
calculating a recommendation score by summing the product of each amount with its corresponding weighting factor;
determining that the candidate affinity item is related to the target item based on the recommendation score; and
displaying the target item and candidate affinity item together on a webpage as related items,wherein the above steps are performed by a computer processor.
4 Assignments
0 Petitions
Accused Products
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.
61 Citations
15 Claims
-
1. A method of identifying related items, comprising:
-
monitoring actions performed on a plurality of items by a plurality of users across a plurality of websites; selecting from the plurality of items, a target item; selecting, from the plurality of items, a candidate affinity item; determining whether the candidate affinity item is related to the target item using the following analysis; calculating, from the plurality of users, across a plurality of websites; a first amount, representing how many users viewed the target item and the candidate affinity item in the same browsing session; a second amount, representing how many users viewed the target item and bought the candidate affinity item in the same browsing session; a third amount, representing how many users bought the target item and the candidate affinity item in different browsing sessions; and a fourth amount, representing how many users did not buy the target item after adding it to their shopping cart but did buy the candidate affinity item in the same browsing session; receiving, for each of the four amounts, a corresponding weighting factor; calculating a recommendation score by summing the product of each amount with its corresponding weighting factor; determining that the candidate affinity item is related to the target item based on the recommendation score; and displaying the target item and candidate affinity item together on a webpage as related items, wherein the above steps are performed by a computer processor. - View Dependent Claims (2, 3, 4, 5, 7, 8, 9, 10)
-
-
6. A computer readable medium embodying a set of instructions thereon, the set of instructions when executed by a computer processor performs the steps of:
-
monitoring actions performed on a plurality of items by a plurality of users across a plurality of websites; selecting, from the plurality of items, a target item; and selecting, from the plurality of items, a candidate affinity item; determining whether the candidate affinity item is related to the target item using the following analysis; calculating, from the plurality of users, across a plurality of websites; a first amount, representing how many users viewed the target item and the candidate affinity item in the same browsing session; a second amount, representing how many users viewed the target item and bought the candidate affinity item in the same browsing session; a third amount, representing how many users bought the target item and the candidate affinity item in different browsing sessions; and a fourth amount, representing how many users did not buy the target item after adding it to their shopping cart but did buy the candidate affinity item in the same browsing session; receiving, for each of the four amounts, a corresponding weighting factor calculating a recommendation score by summing the product of each amount with its corresponding weighting factor; determining that the candidate affinity item is related to the target item based on the recommendation score; and displaying the target item and candidate affinity item together on a web age as related items.
-
-
11. A device for identifying related items, comprising:
-
a processor; a memory coupled to the processor, the memory comprising a set of instructions that cause the processor to perform the steps of; monitoring actions performed on a plurality of items by a plurality of users across a plurality of websites; selecting, from the plurality of items, a target item; and selecting, from the plurality of items, a candidate affinity item; determining whether the candidate affinity item is related to the target item using the following analysis; calculating, from the plurality of users, across a plurality of websites; a first amount, representing how many users viewed the target item and the candidate affinity item in the same browsing session; a second amount, representing how many users viewed the target item and bought the candidate affinity item in the same browsing session; a third amount, representing how many users bought the target item and the candidate affinity item in different browsing sessions; and a fourth amount, representing how many users did not buy the target item after adding it to their shopping cart but did buy the candidate affinity item in the same browsing session; receiving, for each of the four amounts, a corresponding weighting factor calculating a recommendation score by summing the product of each amount with its corresponding weighting factor; determining that the candidate affinity item is related to the target item based on the recommendation score; and displaying the target item and candidate affinity item together on a web age as related items. - View Dependent Claims (12, 13, 14, 15)
-
Specification