System For Individualized Customer Interaction

Abstract

A method and system for using individualized customer models when operating a retail establishment is provided. The individualized customer models may be generated using statistical analysis of transaction data for the customer, thereby generating sub-models and attributes tailored to customer. The individualized customer models may be used in any aspect of a retail establishment's operations, ranging from supply chain management issues, inventory control, promotion planning (such as selecting parameters for a promotion or simulating results of a promotion), to customer interaction (such as providing a shopping list or providing individualized promotions).

1 . (canceled) 
     
     
         2 . A computer-implemented method for evaluating performance of a shopping list predictor, the method comprising:
 accessing a customer model that stores transaction data associated with a customer, wherein the transaction data describes previous purchases that were made by the customer;   determining, by one or more computers, at least one performance metric to be used for evaluating the shopping list predictor;   determining, from the transaction data, training data to be used for training the shopping list predictor and test data to be used for evaluating the performance of the shopping list predictor;   generating, by the one or more computers and based on the training data, a predicted shopping list using the shopping list predictor;   comparing, by the one or more computers, the predicted shopping list with the test data to determine a match between product categories that were predicted by the shopping list predictor with product categories that were actually purchased by the customer;   determining a value of a performance metric based on comparing the predicted shopping list with the test data; and   outputting, by the one or more computers, a measure of performance for the shopping list predictor based on the value of the performance metric.   
     
     
         3 . The computer-implemented method of  claim 2 , wherein the at least one performance metric comprises at least one of a standard recall, a precision, an accuracy, or an f-measure. 
     
     
         4 . The computer-implemented method of  claim 2 , wherein generating a predicted shopping list comprises predicting a probability that the customer will purchase a product from a particular product category. 
     
     
         5 . The computer-implemented method of  claim 2 , wherein generating a predicted shopping list comprises:
 determining, based on the training data, at least one attribute to be used in generating a predicted shopping list; and   generating, based on the determined at least one attributes, a prediction of a product category containing a product that the customer will likely acquire on a shopping trip.   
     
     
         6 . The computer-implemented method of  claim 5 , wherein determining the at least one attribute comprises applying one or more rules to the training data to determine the at least one attribute. 
     
     
         7 . The computer-implemented method of  claim 5 , wherein determining the at least one attribute comprises applying machine learning to the training data to determine the at least one attribute. 
     
     
         8 . A system comprising one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to perform operations for evaluating performance of a shopping list predictor, the operations comprising:
 accessing a customer model that stores transaction data associated with a customer, wherein the transaction data describes previous purchases that were made by the customer;   determining at least one performance metric to be used for evaluating the shopping list predictor;   determining, from the transaction data, training data to be used for training the shopping list predictor and test data to be used for evaluating the performance of the shopping list predictor;   generating, based on the training data, a predicted shopping list using the shopping list predictor;   comparing, the predicted shopping list with the test data to determine a match between product categories that were predicted by the shopping list predictor with product categories that were actually purchased by the customer;   determining a value of a performance metric based on comparing the predicted shopping list with the test data; and   outputting a measure of performance for the shopping list predictor based on the value of the performance metric.   
     
     
         9 . The system of  claim 8 , wherein the at least one performance metric comprises at least one of a standard recall, a precision, an accuracy, or an f-measure. 
     
     
         10 . The system of  claim 8 , wherein generating a predicted shopping list comprises predicting a probability that the customer will purchase a product from a particular product category. 
     
     
         11 . The system of  claim 8 , wherein generating a predicted shopping list comprises:
 determining, based on the training data, at least one attribute to be used in generating a predicted shopping list; and   generating, based on the determined at least one attributes, a prediction of a product category containing a product that the customer will likely acquire on a shopping trip.   
     
     
         12 . The system of  claim 11 , wherein determining the at least one attribute comprises applying one or more rules to the training data to determine the at least one attribute. 
     
     
         13 . The system of  claim 11 , wherein determining the at least one attribute comprises applying machine learning to the training data to determine the at least one attribute. 
     
     
         14 . A computer program product encoded on one or more non-transitory computer storage media, the computer program product comprising instructions that when executed by one or more computers cause the one or more computers to perform operations for evaluating performance of a shopping list predictor, the operations comprising:
 accessing a customer model that stores transaction data associated with a customer, wherein the transaction data describes previous purchases that were made by the customer;   determining at least one performance metric to be used for evaluating the shopping list predictor;   determining, from the transaction data, training data to be used for training the shopping list predictor and test data to be used for evaluating the performance of the shopping list predictor;   generating, based on the training data, a predicted shopping list using the shopping list predictor;   comparing, the predicted shopping list with the test data to determine a match between product categories that were predicted by the shopping list predictor with product categories that were actually purchased by the customer;   determining a value of a performance metric based on comparing the predicted shopping list with the test data; and   outputting a measure of performance for the shopping list predictor based on the value of the performance metric.   
     
     
         15 . The computer program product of  claim 14 , wherein the at least one performance metric comprises at least one of a standard recall, a precision, an accuracy, or an f-measure. 
     
     
         16 . The computer program product of  claim 14 , wherein generating a predicted shopping list comprises predicting a probability that the customer will purchase a product from a particular product category. 
     
     
         17 . The computer program product of  claim 14 , wherein generating a predicted shopping list comprises:
 determining, based on the training data, at least one attribute to be used in generating a predicted shopping list; and   generating, based on the determined at least one attributes, a prediction of a product category containing a product that the customer will likely acquire on a shopping trip.   
     
     
         18 . The computer program product of  claim 17 , wherein determining the at least one attribute comprises applying one or more rules to the training data to determine the at least one attribute. 
     
     
         19 . The computer program product of  claim 17 , wherein determining the at least one attribute comprises applying machine learning to the training data to determine the at least one attribute.