Intelligent offer for related products with preview and real time feedback

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.

1 . A method for recommending affinity products, the method comprising:
 collecting, in a server system, data corresponding to monitored actions on a web site;   providing an identification of affinity products based on said monitored actions relating to a target product;   providing a preview of an identified affinity product;   modifying the selection of said identified affinity product; and   providing an updated preview showing any change in said affinity product due to said modifying.   
     
     
         2 . The method as recited in  claim 1  further comprising:
 providing a formula having weightings for identifying affinity products based on said monitored actions; 
 providing a preview of an affinity product identified according to said formula; 
 varying said weightings; and 
 providing an updated preview showing any change in said affinity product due to said varying of said weightings. 
 
     
     
         3 . The method as recited in  claim 2 , wherein said formula includes an exclusion of selected products. 
     
     
         4 . The method as recited in  claim 2 , wherein said 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 brought said first product. 
     
     
         5 . The method as recited in  claim 2 , wherein said monitored actions include keywords, and said affinity product is a product on which action was taken by a group of users who used the same keyword. 
     
     
         6 . The method as recited in  claim 1  further comprising:
 providing a plurality of affinity products for each target product. 
 
     
     
         7 . The method as recited in  claim 1 , wherein said preview comprises a listing of a plurality of target products, with at least one affinity produce associated therewith. 
     
     
         8 . A method for tracking web usage data in real time, the method comprising:
 collecting, in a server system, real time data corresponding to monitored actions on a web site, said monitored actions including buying a recommended product;   aggregating said real time data into aggregate groups desired for display;   storing said aggregated real time data in a hierarchical structure in a RAM in said server system; and   providing said real time data from said RAN to a client at a client computer.   
     
     
         9 . The method as recited in  claim 8  further comprising:
 providing an identification of affinity products based on said monitored actions relating to a target product; 
 providing a preview of an identified affinity product; 
 modifying the selection of said identified affinity product based on said real time data; and 
 providing an updated preview showing any change in said affinity product due to said modifying. 
 
     
     
         10 . A method for recommending affinity products, the method comprising:
 collecting, in a server system, data corresponding to monitored actions on a web site;   providing a formula for identifying affinity products based on said monitored actions;   tracking said monitored actions for an identified segment of users; and   identifying said affinity product from monitored actions of said segment of users.   
     
     
         11 . The method as recited in  claim 10 , 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. 
     
     
         12 . The method as recited in  claim 10  further comprising:
 providing an identification of affinity products based on said monitored actions relating to a target product; 
 providing a preview of an identified affinity product; 
 modifying the selection of said identified affinity product; and 
 providing an updated preview showing any change in said affinity product due to said modifying. 
 
     
     
         13 . The method as recited in  claim 10  further comprising:
 collecting, in a server system, real time data corresponding to said monitored actions on a web site; 
 aggregating said real time data into aggregate groups desired for display; 
 storing said aggregated real time data in a hierarchical structure in a RAM in said server system; and 
 providing said real time data from said RAM to a client at a client computer.