Fit recommendation via collaborative inference

Abstract

Some embodiments of the invention provide techniques for recommending a size of a subject item to fit a subject consumer. In some embodiments, clusters of consumers with fit characteristics similar to the subject consumer are identified, using one or more data clustering algorithms, based on any of numerous consumer attributes (e.g., self-reported and/or inferred height, weight, body shape, body characteristics, and/or purchase histories (e.g., consumers with high overlap in terms of sets of products purchased)). Information on other consumers in the cluster may be analyzed to draw conclusions on how different sizes of the subject item may fit the subject consumer. For example, the purchase history of other members of the cluster may be analyzed to determine whether other members purchased a particular size of the item, and if so, the size purchased by the other members may serve as a basis to recommend a size that may best fit the consumer. For example, if other members of the cluster purchased a particular size, then that size may be recommended to the subject consumer, or if other members of the cluster purchased and then returned a particular size (e.g., for being too small), then another (e.g., larger) size may be recommended to the subject consumer.

What is claimed is: 
     
         1 . A method of employing at least one computer to generate a recommendation, for a subject consumer, of a version of a subject item for which a plurality of versions is available, the method comprising:
 (A) receiving at the at least one computer a request for a recommendation of a version of the subject item to suit the subject consumer;   (B) identifying, by the at least one computer, a cluster of items to which the subject item belongs, and analyzing information relating to the cluster of items;   (C) determining, by the at least one computer, whether a recommendation of a version of the subject item is to be made as a result of the analyzing in (B);   (D) if it is determined in (C) that a recommendation of a version of the subject item is not to be made as a result of the analyzing in (B), identifying, using the at least one computer, a cluster of consumers to which the subject consumer belongs, and analyzing information relating to the cluster of consumers;   (E) determining, by the at least one computer, whether a recommendation of a version of the subject item is to be made as a result of the analyzing in (D); and   (F) if it is determined in (C) or in (E) that a recommendation of a version of the subject item is to be made, using the at least one computer to generate a recommendation for a version of the subject item likely to suit the subject consumer.   
     
     
         2 . The method of  claim 1 , wherein the cluster of items identified in the act (B) comprises items purchased by the plurality of consumers, and wherein the analyzing in the act (B) comprises analyzing information relating to purchases and/or returns by the plurality of consumers of at least one other item in the cluster of items to determine a version of the subject item likely to suit the subject consumer. 
     
     
         3 . The method of  claim 2 , wherein the analyzing comprises employing a relationship between versions of the subject item and versions of the at least one other item in the cluster to determine a version of the subject item likely to suit the subject consumer. 
     
     
         4 . The method of  claim 1 , wherein the identifying in the act (D) comprises identifying a cluster of consumers that is defined by commonality with respect to one or more attributes comprising self-reported and/or inferred body measurements, body shape attributes, and/or sales history. 
     
     
         5 . The method of  claim 1 , wherein the identifying in the act (D) comprises identifying a plurality of clusters of consumers to which the subject consumer belongs, each of the plurality of clusters being defined by commonality with respect to a different consumer attribute. 
     
     
         6 . The method of  claim 1 , wherein the analyzing in the act (D) comprises determining whether a version of the subject item has been successfully purchased by at least one other consumer in the cluster. 
     
     
         7 . The method of  claim 6 , wherein the determining comprises determining whether a version of the subject item was designated as a favorite by the at least one other consumer. 
     
     
         8 . The method of  claim 1 , wherein the act (F) comprises providing an indication of confidence that the version of the subject item will suit the subject consumer. 
     
     
         9 . The method of  claim 8 , wherein the act (F) comprises providing an indication of confidence that the version of the subject item will suit the subject consumer along each of a plurality of dimensions. 
     
     
         10 . The method of  claim 1 , wherein the subject item is an item of apparel or a pair of shoes. 
     
     
         11 . At least one computer-readable storage device having instruction recorded thereon which, when executed, perform a method of generating a recommendation, for a subject consumer, of a version of a subject item for which a plurality of versions is available, the method comprising:
 (A) receiving a request for a recommendation of a version of the subject item to suit the subject consumer;   (B) identifying a cluster of items to which the subject item belongs, and analyzing information relating to the cluster of items;   (C) determining whether a recommendation of a version of the subject item is to be made as a result of the analyzing in (B);   (D) if it is determined in (C) that a recommendation of a version of the subject item is not to be made as a result of the analyzing in (B), identifying a cluster of consumers to which the subject consumer belongs, and analyzing information relating to the cluster of consumers;   (E) determining whether a recommendation of a version of the subject item is to be made as a result of the analyzing in (D); and   (F) if it is determined in (C) or in (E) that a recommendation of a version of the subject item is to be made, generating a recommendation for a version of the subject item likely to suit the subject consumer.   
     
     
         12 . The at least one computer-readable storage device of  claim 11 , wherein the cluster of items identified in the act (B) comprises items purchased by the plurality of consumers, and wherein the analyzing in the act (B) comprises analyzing information relating to purchases and/or returns by the plurality of consumers of at least one other item in the cluster of items to determine a version of the subject item likely to suit the subject consumer. 
     
     
         13 . The at least one computer-readable storage device of  claim 12 , wherein the analyzing comprises employing a relationship between versions of the subject item and versions of the at least one other item in the cluster to determine a version of the subject item likely to suit the subject consumer. 
     
     
         14 . The at least one computer-readable storage device of  claim 11 , wherein the identifying in the act (D) comprises identifying a cluster of consumers that is defined by commonality with respect to one or more attributes comprising self-reported and/or inferred body measurements, body shape attributes, and/or sales history. 
     
     
         15 . The at least one computer-readable storage device of  claim 11 , wherein the identifying in the act (D) comprises identifying a plurality of clusters of consumers to which the subject consumer belongs, each of the plurality of clusters being defined by commonality with respect to a different consumer attribute. 
     
     
         16 . The at least one computer-readable storage device of  claim 11 , wherein the analyzing in the act (D) comprises determining whether a version of the subject item has been successfully purchased by at least one other consumer in the cluster. 
     
     
         17 . The at least one computer-readable storage device of  claim 16 , wherein the determining comprises determining whether a version of the subject item was designated as a favorite by the at least one other consumer. 
     
     
         18 . The at least one computer-readable storage device of  claim 11 , wherein the act (F) comprises providing an indication of confidence that the version of the subject item will suit the subject consumer. 
     
     
         19 . The at least one computer-readable storage device of  claim 18 , wherein the act (F) comprises providing an indication of confidence that the version of the subject item will suit the subject consumer along each of a plurality of dimensions. 
     
     
         20 . The at least one computer-readable storage device of  claim 11 , wherein the subject item is an item of apparel or a pair of shoes. 
     
     
         21 . A computer system for generating a recommendation, for a subject consumer, of a version of a subject item for which a plurality of versions is available, the computer system comprising:
 at least one computer processor programmed to:
 receive a request for a recommendation of a version of the subject item to suit the subject consumer; 
 identify a cluster of items to which the subject item belongs, and analyzing information relating to the cluster of items; 
 determine whether a recommendation of a version of the subject item is to be made as a result of analyzing the information relating to the cluster of items; 
 if it is determined that a recommendation of a version of the subject item is not to be made as a result of analyzing the information relating to the cluster of items, identify a cluster of consumers to which the subject consumer belongs, and analyzing information relating to the cluster of consumers; 
 determine whether a recommendation of a version of the subject item is to be made as a result of analyzing the information relating to the cluster of consumers; and 
 if it is determined that a recommendation of a version of the subject item is to be made as a result of analyzing the information relating to the cluster of items or as a result of analyzing the information relating to the cluster of consumers, generate a recommendation for a version of the subject item likely to suit the subject consumer. 
   
     
     
         22 . The computer system of  claim 21 , wherein the cluster of items identified in the act (B) comprises items purchased by the plurality of consumers, and wherein analyzing information relating to the cluster of items comprises analyzing information relating to purchases and/or returns by the plurality of consumers of at least one other item in the cluster of items to determine a version of the subject item likely to suit the subject consumer. 
     
     
         23 . The computer system of  claim 22 , wherein analyzing information relating to the cluster of items comprises employing a relationship between versions of the subject item and versions of the at least one other item in the cluster to determine a version of the subject item likely to suit the subject consumer. 
     
     
         24 . The computer system of  claim 21 , wherein identifying the cluster of consumers comprises identifying a cluster of consumers that is defined by commonality with respect to one or more attributes comprising self-reported and/or inferred body measurements, body shape attributes, and/or sales history. 
     
     
         25 . The computer system of  claim 21 , wherein identifying the cluster of consumers comprises identifying a plurality of clusters of consumers to which the subject consumer belongs, each of the plurality of clusters being defined by commonality with respect to a different consumer attribute. 
     
     
         26 . The computer system of  claim 21 , wherein analyzing information relating to the cluster of consumers comprises determining whether a version of the subject item has been successfully purchased by at least one other consumer in the cluster. 
     
     
         27 . The computer system of  claim 26 , wherein the determining comprises determining whether a version of the subject item was designated as a favorite by the at least one other consumer. 
     
     
         28 . The computer system of  claim 21 , wherein generating the recommendation comprises providing an indication of confidence that the version of the subject item will suit the subject consumer. 
     
     
         29 . The computer system of  claim 28 , wherein generating the recommendation comprises providing an indication of confidence that the version of the subject item will suit the subject consumer along each of a plurality of dimensions. 
     
     
         30 . The computer system of  claim 21 , wherein the subject item is an item of apparel or a pair of shoes. 
     
     
         31 . A computer system for making a recommendation to a subject consumer, the computer system comprising:
 at least one computer processor programmed to:
 receive a request from the subject consumer for a recommendation relating to a first item; 
 determine that a recommendation relating to the first item cannot be made to the subject consumer; 
 determine that a recommendation relating to a second item, different than the first item, can be made to the subject consumer; and 
 cause the recommendation relating to the second item to be transmitted to the subject consumer. 
   
     
     
         32 . The computer system of  claim 31 , wherein one or more of determining that a recommendation relating to the first item cannot be made to the subject consumer and determining that a recommendation relating to a second item can be made to the subject consumer comprises identifying a cluster of consumers to which the subject consumer belongs, and analyzing information relating to the cluster of consumers. 
     
     
         33 . The computer system of  claim 31 , wherein determining that a recommendation relating to the first item cannot be made to the subject consumer comprises identifying a cluster of items to which the first item belongs, and analyzing information relating to the cluster of items. 
     
     
         34 . The computer system of  claim 31 , wherein determining that a recommendation relating to the first item cannot be made to the subject consumer comprises determining that no version of the first item suits the subject consumer. 
     
     
         35 . The computer system of  claim 31 , wherein determining that a recommendation relating to a second item can be made to the subject consumer comprises identifying a cluster of items to which the second item belongs, and analyzing information relating to the cluster of items. 
     
     
         36 . The computer system of  claim 35 , wherein the cluster of items to which the second item belongs comprises items purchased by the plurality of consumers, and wherein determining that a recommendation relating to a second item can be made to the subject consumer comprises analyzing information relating to purchases and/or returns by the plurality of consumers of a version of at least one item in the cluster of items other than the second item to determine a version of the second item likely to suit the subject consumer. 
     
     
         37 . The computer system of  claim 31 , wherein causing the recommendation relating to the second item to be transmitted to the subject consumer comprises causing an indication of confidence that the second item will suit the subject consumer to be transmitted to the subject consumer. 
     
     
         38 . The computer system of  claim 37 , wherein causing the recommendation relating to the second item to be transmitted to the subject consumer comprises causing an indication of confidence that the second item will suit the subject consumer along each of a plurality of dimensions to be transmitted to the subject consumer. 
     
     
         39 . The at least one computer-readable storage device of  claim 31 , wherein the second item is an item of apparel or a pair of shoes.