Systems and methods for garment size recommendation

Abstract

Disclosed are methods, systems, and non-transitory computer-readable medium for generating recommendations regarding products. A method may include determining a set of content features including one or more product attributes; determining a set of latent features; receiving a query user identifier and a query product identifier; determining a feature vector associated with the query user identifier and the query product identifier based on the set of content features and the set of latent features; determining one or more model coefficients for a linear model; and utilizing the linear model to determine a fit score for the query user identifier and the query product identifier.

What is claimed is: 
     
         1 - 20 . (canceled) 
     
     
         21 . A computer-implemented method comprising:
 obtaining, by one or more processors, feedback or transaction data associated with a user, the feedback or transaction data including a plurality of data points;   determining, by the one or more processors, that the plurality of data points exceed a predetermined threshold by comparing the plurality of data points with the predetermined threshold;   determining, by a size recommendation model, one or more fit scores for an article, wherein the article is associated with a unique article identifier;   determining, by the size recommendation model, a highest fit score of the one or more fit scores by comparing measurements for the article to a range of user measurements to determine that the measurements for the article fall within the range of user measurements, the range of user measurements based on a profile of the user; and   generating, by the size recommendation model, a fit recommendation for the article based on the highest fit score.   
     
     
         22 . The computer-implemented method of  claim 21 , further comprising:
 inputting, into the size recommendation model, the feedback or transaction data as training data.   
     
     
         23 . The computer-implemented method of  claim 22 , wherein the size recommendation model is a parameterized model that was trained based on the training data. 
     
     
         24 . The computer-implemented method of  claim 23 , further comprising:
 determining, by the parameterized model, the one or more fit scores for the article.   
     
     
         25 . The computer-implemented method of  claim 21 , wherein the unique article identifier corresponds to the article depicted in a product page. 
     
     
         26 . The computer-implemented method of  claim 21 , the plurality of data points corresponding to at least one instance of feedback data or transaction data associated with the article being provided by the user. 
     
     
         27 . The computer-implemented method of  claim 21 , further comprising:
 determining, by the one or more processors, that the plurality of data points do not exceed the predetermined threshold by comparing the plurality of data points with the predetermined threshold; and   generating, by a content-based approach, the fit recommendation for the article.   
     
     
         28 . The computer-implemented method of  claim 27 , wherein the content-based approach includes determining a recommended unique article identifier based on the profile of the user or at least one garment attribute. 
     
     
         29 . The computer-implemented method of  claim 21 , further comprising:
 determining, by the size recommendation model, that the measurements for the article do not fall within the range of user measurements by comparing the measurements for the article to the range of user measurements, the range of user measurements based on the profile of the user; and   determining, by a content-based approach, a recommended unique article identifier.   
     
     
         30 . A system comprising:
 a memory, storing instructions; and   a processor operatively connected to the memory and configured to execute the instructions to perform operations including:
 obtaining, by one or more processors, feedback or transaction data associated with a user, the feedback or transaction data including a plurality of data points; 
 determining, by the one or more processors, that the plurality of data points exceed a predetermined threshold by comparing the plurality of data points with the predetermined threshold; 
 determining, by a size recommendation model, one or more fit scores for an article, wherein the article is associated with a unique article identifier; 
 determining, by the size recommendation model, a highest fit score of the one or more fit scores by comparing measurements for the article to a range of user measurements to determine that the measurements for the article fall within the range of user measurements, the range of user measurements based on a profile of the user; and 
 generating, by the size recommendation model, a fit recommendation for the article based on the highest fit score. 
   
     
     
         31 . The system of  claim 30 , further comprising:
 inputting, into the size recommendation model, the feedback or transaction data as training data.   
     
     
         32 . The system of  claim 31 , wherein the size recommendation model is a parameterized model that is trained based on the training data. 
     
     
         33 . The system of  claim 32 , further comprising:
 determining, by the parameterized model, the one or more fit scores for the article.   
     
     
         34 . The system of  claim 30 , wherein the unique article identifier corresponds to the article depicted in a product page. 
     
     
         35 . The system of  claim 30 , the plurality of data points corresponding to at least one instance of feedback data or transaction data associated with the article being provided by the user. 
     
     
         36 . The system of  claim 30 , further comprising:
 determining, by the one or more processors, that the plurality of data points do not exceed the predetermined threshold by comparing the plurality of data points with the predetermined threshold; and   generating, by a content-based approach, the fit recommendation for the article.   
     
     
         37 . The system of  claim 36 , wherein the content-based approach includes determining a recommended unique article identifier based on the profile of the user or at least one garment attribute. 
     
     
         38 . A computer-implemented method comprising:
 determining, by a size recommendation model, one or more fit scores for an article, wherein the article is associated with a unique article identifier;   determining, by the size recommendation model, a highest fit score of the one or more fit scores by comparing measurements for the article to a range of user measurements to determine that the measurements for the article fall within the range of user measurements, the range of user measurements based on a profile of a user;   generating, by the size recommendation model, a fit recommendation for the article based on the highest fit score; and   storing, by a data storage device, the fit recommendation for the article to the profile of the user.   
     
     
         39 . The computer-implemented method of  claim 38 , further comprising:
 determining, by the size recommendation model, that the measurements for the article do not fall within the range of user measurements by comparing measurements for the article to the range of user measurements, the range of user measurements based on the profile of the user; and   determining, by a content-based approach, a recommended unique article identifier.   
     
     
         40 . The computer-implemented method of  claim 38 , wherein the unique article identifier corresponds to the article depicted in a product page.