Methods and systems for determining a quantity and a size distribution of products

Abstract

A computer-implemented method may include obtaining article information associated with the one or more articles; obtaining historical transactional data associated with purchasing the one or more articles; obtaining, via the one or more processors, article preference data associated with purchasing the one or more articles; determining, via the one or more processors, one or more assumptions based on the article preference data; determining, via the one or more processors, the quantity associated with purchasing the one or more articles based on the article information and the one or more assumptions; determining, via the one or more processors, the size distribution associated with purchasing the one or more articles based on the determined quantity, the historical transactional data, and the one or more assumptions; and transmitting, to a purchaser, a notification indicating the quantity and the size distribution associated with purchasing the one or more articles.

1 - 20 . (canceled) 
     
     
         21 . A computer-implemented method for determining a recommended quantity and a size distribution associated with one or more articles, the method comprising:
 training a machine learning model to map input variables to the recommended quantity associated with the one or more articles, the recommended quantity indicating a number of articles to be made available through an electronic platform;   executing the machine learning model to determine the recommended quantity associated with the one or more articles, the determining based on article information and one or more assumptions of demand;   executing the machine learning model to determine the size distribution associated with the one or more articles based on the recommended quantity, historical transactional data, and the one or more assumptions of demand;   subsequently training the machine learning model using the size distribution associated with the one or more articles based on the recommended quantity, the historical transactional data, and the one or more assumptions of demand; and   in accordance with the subsequently training, displaying a notification indicating the recommended quantity and the size distribution associated with the one or more articles.   
     
     
         22 . The computer-implemented method of  claim 21 , wherein the machine learning model is trained with at least one training set to determine the recommended quantity. 
     
     
         23 . The computer-implemented method of  claim 21 , wherein the machine learning model is trained with at least one training set to determine the size distribution. 
     
     
         24 . The computer-implemented method of  claim 21 , wherein the input variables comprises one or more attributes, the one or more attributes including a likelihood prediction of one or more service users requesting the one or more articles of an article category. 
     
     
         25 . The computer-implemented method of  claim 21 , wherein the historical transactional data includes previous transaction data, at least one historical rental demand metric, and a historical size distribution associated with the one or more articles. 
     
     
         26 . The computer-implemented method of  claim 21 , wherein the article information comprises whether the one or more articles belong to a minimum order quantity category. 
     
     
         27 . The computer-implemented method of  claim 21 , wherein the article information comprises whether the one or more articles belong to a pre-pack category. 
     
     
         28 . The computer-implemented method of  claim 21 , wherein the one or more assumptions of demand include one or more numerical values associated with one or more article attributes. 
     
     
         29 . The computer-implemented method of  claim 21 , wherein the one or more assumptions of demand are updated periodically. 
     
     
         30 . The computer-implemented method of  claim 21 , wherein the one or more assumptions of demand are based on article preference data. 
     
     
         31 . The computer-implemented method of  claim 31 , wherein the article preference data comprises season impact data that indicates seasonal impact on a trend or service user preference for the one or more articles. 
     
     
         32 . A computer system for determining a recommended quantity and a size distribution associated with one or more articles, comprising:
 a memory storing instructions; and   one or more processors configured to execute the instructions to perform operations including:
 training a machine learning model to map input variables to the recommended quantity associated with the one or more articles, the recommended quantity indicating a number of articles to be made available through an electronic platform; 
 executing the machine learning model to determine the recommended quantity associated with the one or more articles, the determining based on article information and one or more assumptions of demand; 
 executing the machine learning model to determine the size distribution associated with the one or more articles based on the recommended quantity, historical transactional data, and the one or more assumptions of demand; 
 subsequently training the machine learning model using the size distribution associated with the one or more articles based on the recommended quantity, the historical transactional data, and the one or more assumptions of demand; and 
 in accordance with the subsequently training, displaying a notification indicating the recommended quantity and the size distribution associated with the one or more articles. 
   
     
     
         33 . The computer system of  claim 32 , wherein the machine learning model is trained with at least one training set to determine the recommended quantity. 
     
     
         34 . The computer system of  claim 32 , wherein the machine learning model is trained with at least one training set to determine the size distribution. 
     
     
         35 . The computer system of  claim 32 , wherein the input variables comprises one or more attributes, the one or more attributes including a likelihood prediction of one or more service users requesting the one or more articles of an article category. 
     
     
         36 . The computer system of  claim 32 , wherein the size distribution indicates how the determined quantity distributes among one or more sizes of an article category. 
     
     
         37 . A non-transitory computer readable medium for use on a computer system containing computer-executable programming instructions for performing a method of determining a recommended quantity and a size distribution associated with one or more articles, the method comprising:
 training a machine learning model to map input variables to the recommended quantity associated with the one or more articles, the recommended quantity indicating a number of articles to be made available through an electronic platform;   executing the machine learning model to determine the recommended quantity associated with the one or more articles, the determining based on article information and one or more assumptions of demand;   executing the machine learning model to determine the size distribution associated with the one or more articles based on the recommended quantity, historical transactional data, and the one or more assumptions of demand;   subsequently training the machine learning model using the size distribution associated with the one or more articles based on the recommended quantity, the historical transactional data, and the one or more assumptions of demand; and   in accordance with the subsequently training, displaying a notification indicating the recommended quantity and the size distribution associated with the one or more articles.   
     
     
         38 . The non-transitory computer readable medium of  claim 37 , wherein the machine learning model is trained with at least one training set to determine the recommended quantity. 
     
     
         39 . The non-transitory computer readable medium of  claim 37 , wherein the machine learning model is trained with at least one training set to determine the size distribution. 
     
     
         40 . The non-transitory computer readable medium of  claim 37 , wherein the input variables comprises one or more attributes, the one or more attributes including a likelihood prediction of one or more service users requesting the one or more articles of an article category.