System and Method for a Service Sentiment Indictor

Abstract

At least some embodiments are directed to a system that receives data generated when point of sale terminals are used. The point of sale terminals are associated with multiple merchants. The system generates a quantitative data from the received data. The system computes a quality of service score of a first merchant based on the quantitative data. The system generates an item data structure storing values that correlate multiple users with multiple merchants at least based on the quality of service score. The system determines users that are shared by multiple merchants and computes a customer relevance value associated with the user and the first merchant. The system outputs a user-specific recommendation associated with a second merchant to a user computing device, wherein the user-specific recommendation is computed at least in part based on the customer relevance value associated with the first merchant.

What is claimed is: 
     
         1 . An apparatus comprising:
 a processor;   and a non-transitory memory storing instructions which, when executed by the processor, cause the processor to:
 receive a first plurality of quantitative data associated with activities performed by a plurality of users, wherein the first plurality of quantitative data is generated when a plurality of cards is used with a plurality of point of sale terminals coupled to the processor via a network; 
 utilize the first plurality of quantitative data to compute a second plurality of quantitative data associated with the plurality of users; 
 utilize the second plurality of quantitative data to compute a quality of service score associated with a first merchant from a plurality of merchants; 
 utilize at least one weighted item value associated with the first merchant, wherein the at least one weighted item is computed at least based on the quality of service score and an aggregated spending of a user from the plurality of users, and wherein the aggregated spending is associated with the first merchant; 
 generate an item data structure comprising a plurality of values that correlate the plurality of users with the plurality of merchants, wherein the item data structure comprises the weighted item value; 
 generate an item-to-item similarity data structure comprising a plurality of values indicative of users from the plurality of users shared between the plurality of merchants; 
 compute a customer relevance value as a product of the item data structure and the item-to-item similarity data structure, wherein the customer relevance value is associated with the user and the first merchant, and wherein the customer relevance value indicates a probability of a relation between the user and the first merchant; and 
   output a user-specific recommendation associated with a second merchant from the plurality of merchants to a user computing device coupled to the network, wherein the user-specific recommendation is computed at least in part based on the customer relevance value associated with the first merchant.   
     
     
         2 . The apparatus of  claim 1 , wherein the at least one weighted item is further computed based on demographic data associated with the user. 
     
     
         3 . The apparatus of  claim 1 , wherein the plurality of users shared between the plurality of merchants is inferred based on a plurality of activities performed by the plurality of users tracked by the processor via the plurality of point of sale terminals. 
     
     
         4 . The apparatus of  claim 1 , wherein the second plurality of quantitative data is a gratuity amount associated with the user from a plurality of user and the first merchant. 
     
     
         5 . The apparatus of  claim 1 , wherein the customer relevance value indicates a probability of a relation between the user and the first merchant, and wherein the relation indicates the likelihood that the user has an interest in an item associated with the first merchant. 
     
     
         6 . The apparatus of  claim 1 , wherein the users shared between the plurality of merchants indicates that the users have executed at least one transaction with each merchant from the plurality of merchants. 
     
     
         7 . The apparatus of  claim 1 , wherein the item-to-item similarity data structure is generated at least based on a mean record of charge between the plurality of users and the plurality of merchants. 
     
     
         8 . A method comprising:
 receiving, by a processor, a first plurality of quantitative data associated with activities performed by a plurality of users, wherein the first plurality of quantitative data is generated when a plurality of cards is used with a plurality of point of sale terminals coupled to the processor via a network;   utilizing, by the processor, the first plurality of quantitative data to compute a second plurality of quantitative data associated with the plurality of users;   utilizing, by the processor, the second plurality of quantitative data to compute a quality of service score associated with a first merchant from a plurality of merchants;   utilizing, by the processor, at least one weighted item value associated with the first merchant, wherein the at least one weighted item is computed at least based on the quality of service score and an aggregated spending of a user from the plurality of users, and wherein the aggregated spending is associated with the first merchant;   generating, by the processor, an item data structure comprising a plurality of values that correlate the plurality of users with the plurality of merchants, wherein the item data structure comprises the weighted item value;   generating, by the processor, an item-to-item similarity data structure comprising a plurality of values indicative of users from the plurality of users shared between the plurality of merchants;   computing, by the processor, a customer relevance value as a product of the item data structure and the item-to-item similarity data structure, wherein the customer relevance value is associated with the user and the first merchant, and wherein the customer relevance value indicates a probability of a relation between the user and the first merchant; and   outputting, by the processor, a user-specific recommendation associated with a second merchant from the plurality of merchants to a user computing device coupled to the network, wherein the user-specific recommendation is computed at least in part based on the customer relevance value associated with the first merchant.   
     
     
         9 . The method of  claim 8 , wherein the at least one weighted item is further computed based on demographic data associated with the user. 
     
     
         10 . The method of  claim 8 , wherein the plurality of users shared between the plurality of merchants is inferred based on a plurality of activities performed by the plurality of users tracked by the processor via the plurality of point of sale terminals. 
     
     
         11 . The method of  claim 8 , wherein the second plurality of quantitative data is a gratuity amount associated with the user from a plurality of user and the first merchant. 
     
     
         12 . The method of  claim 8 , wherein the customer relevance value indicates a probability of a relation between the user and the first merchant, and wherein the relation indicates the likelihood that the user has an interest in an item associated with the first merchant. 
     
     
         13 . The method of  claim 8 , wherein the users shared between the plurality of merchants indicates that the users have executed at least one transaction with each merchant from the plurality of merchants. 
     
     
         14 . The method of  claim 8 , wherein the item-to-item similarity data structure is generated at least based on a mean record of charge between the plurality of users and the plurality of merchants. 
     
     
         15 . A non-transitory computer readable medium comprising instructions which, when executed by a processor, cause the processor to:
 receive a first plurality of quantitative data associated with activities performed by a plurality of users, wherein the first plurality of quantitative data is generated when a plurality of cards is used with a plurality of point of sale terminals coupled to the processor via a network;   utilize the first plurality of quantitative data to compute a second plurality of quantitative data associated with the plurality of users;   utilize the second plurality of quantitative data to compute a quality of service score associated with a first merchant from a plurality of merchants;   utilize at least one weighted item value associated with the first merchant, wherein the at least one weighted item is computed at least based on the quality of service score and an aggregated spending of a user from the plurality of users, and wherein the aggregated spending is associated with the first merchant;   generate an item data structure comprising a plurality of values that correlate the plurality of users with the plurality of merchants, wherein the item data structure comprises the weighted item value;   generate an item-to-item similarity data structure comprising a plurality of values indicative of users from the plurality of users shared between the plurality of merchants;   compute a customer relevance value as a product of the item data structure and the item-to-item similarity data structure, wherein the customer relevance value is associated with the user and the first merchant, and wherein the customer relevance value indicates a probability of a relation between the user and the first merchant; and   output a user-specific recommendation associated with a second merchant from the plurality of merchants to a user computing device coupled to the network, wherein the user-specific recommendation is computed at least in part based on the customer relevance value associated with the first merchant.   
     
     
         16 . The non-transitory computer readable medium of  claim 15 , wherein the at least one weighted item is further computed based on demographic data associated with the user. 
     
     
         17 . The non-transitory computer readable medium of  claim 15 , wherein the plurality of users shared between the plurality of merchants is inferred based on a plurality of activities performed by the plurality of users tracked by the processor via the plurality of point of sale terminals. 
     
     
         18 . The non-transitory computer readable medium of  claim 15 , wherein the second plurality of quantitative data is a gratuity amount associated with the user from a plurality of user and the first merchant. 
     
     
         19 . The non-transitory computer readable medium of  claim 15 , wherein the customer relevance value indicates a probability of a relation between the user and the first merchant, and wherein the relation indicates the likelihood that the user has an interest in an item associated with the first merchant. 
     
     
         20 . The non-transitory computer readable medium of  claim 15 , wherein the users shared between the plurality of merchants indicates that the users have executed at least one transaction with each merchant from the plurality of merchants.