Identifying value conscious users

Abstract

A system comprising one or more processors and one or more non-transitory computer-readable media storing computing instructions, that when executed on the one or more processors, cause the one or more processors to perform operations comprising: identifying a segment of users who are value conscious about a product by: evaluating a number of activities of the users indicating whether or not the users are value conscious for the product; and generating, using a conditional probability equation, a probability that a user of the users will show interest in the product; and transmitting instructions to display, for viewing by the user, a recommendation for the product, wherein the recommendation is based on the probability being above a threshold that the user will show interest in the product. Other embodiments are disclosed herein.

What is claimed is: 
     
         1 . A system comprising:
 one or more processors; and   one or more non-transitory computer-readable media storing computing instructions, that when executed on the one or more processors, cause the one or more processors to perform operations comprising:
 identifying a segment of users who are value conscious about a product by:
 evaluating a number of activities of the users indicating whether or not the users are value conscious for the product; and 
 generating, using a conditional probability equation, a probability that a user of the users will show interest in the product, wherein the conditional probability equation is based on a sequence of equations, wherein each sequential equation of the sequence of equations builds upon an immediately previous equation of the sequence of equations by using data from the immediately previous equation; and 
 
 transmitting instructions to display, for viewing by the user, a recommendation for the product, wherein the recommendation is based on the probability being above a threshold that the user will show interest in the product. 
   
     
     
         2 . The system of  claim 1 , wherein the computing instructions, when executed on the one or more processors, further cause the one or more processors to perform operations comprising:
 retrieving product information from a website database, wherein the product information comprises one or more value-sensitive product attributes derived from product reviews;   identifying the product as a value-sensitive product by at least a value price tag for the product;   detecting, using the product reviews, value consciousness for products that are infrequently purchased;   deriving, using word embedding, latent features of each respective word of one or more of the product reviews associated with the product and a distribution of probabilities over the latent features; and   determining, using historical value-sensitive descriptions, whether each respective word of the product reviews associated with the product is associated with a value-sensitive description.   
     
     
         3 . The system of  claim 1 , wherein generating the probability further comprises using a hill climbing algorithm. 
     
     
         4 . The system of  claim 1 , wherein identifying the segment of the users further comprises identifying first users and second users, wherein the second users are not value conscious about the product. 
     
     
         5 . The system of  claim 4 , wherein the computing instructions, when executed on the one or more processors, further cause the one or more processors to perform operations comprising:
 analyzing shopping histories of the first users and the second users; and   analyzing shopping patterns of the first users and the second users.   
     
     
         6 . The system of  claim 5 , wherein analyzing the shopping patterns for the first users and the second users further comprises:
 analyzing on-line shopping patterns for the first users and the second users, wherein the on-line shopping patterns further comprise at least one of:
 a user purchase history; 
 a user browser activity; 
 a user value conscious webpage visit; or 
 a user profile. 
   
     
     
         7 . The system of  claim 6 , wherein the computing instructions, when executed on the one or more processors, further cause the one or more processors to perform operations comprising:
 leveraging low-rank matrices to infer additional latent features for the first users, the second users, and one or more products to leverage low-rank matrices; and   calculating, using matrix factorization, a behavior of the first users and the second users associated with products that are co-bought.   
     
     
         8 . The system of  claim 1 , wherein transmitting the instructions to display the recommendation for the product further comprises transmitting instructions to update a respective webpage of a website displaying a value-sensitive product. 
     
     
         9 . The system of  claim 1 , wherein:
 the computing instructions, when executing on the one or more processors, further cause the one or more processors to perform operations comprising:
 preparing a first recommendation and a first promotion for the product; and 
 preparing a second recommendation and a second promotion for the product; 
    preparing the first recommendation and the first promotion comprises preparing larger discounts and savings for the first recommendation and the first promotion than for the second recommendation and the second promotion; and    preparing the second recommendation and the second promotion comprises preparing discounts and savings for the second recommendation and the second promotion based on descriptions in user profiles of second users comprising at least one of age, family size, pets, hobbies, geographic location, or gender.   
     
     
         10 . The system of  claim 9 , wherein the computing instructions, when executing on the one or more processors, further cause the one or more processors to perform operations comprising:
 determining whether to display the first recommendation and the first promotion for the product to first users; and   determining whether to display the second recommendation and the second promotion for the product to the second users based on user profiles of the second users.   
     
     
         11 . A method being implemented via execution of computing instructions configured to run on one or more processors and stored at one or more non-transitory media, the method comprising:
 identifying a segment of users who are value conscious about a product by:
 evaluating a number of activities of the users indicating whether or not the users are value conscious for the product; and 
 generating, using a conditional probability equation, a probability that a user of the users will show interest in the product, wherein the conditional probability equation is based on a sequence of equations, wherein each sequential equation of the sequence of equations builds upon an immediately previous equation of the sequence of equations by using data from the immediately previous equation; and 
   transmitting instructions to display, for viewing by the user, a recommendation for the product, wherein the recommendation is based on the probability being above a threshold that the user will show interest in the product.   
     
     
         12 . The method of  claim 11  further comprising:
 retrieving product information from a website database, wherein the product information comprises one or more value-sensitive product attributes derived from product reviews; 
 identifying the product as a value-sensitive product by at least a value price tag for the product; 
 detecting, using the product reviews, value consciousness for products that are infrequently purchased; 
 deriving, using word embedding, latent features of each respective word of one or more of the product reviews associated with the product and a distribution of probabilities over the latent features; and 
 determining, using historical value-sensitive descriptions, whether each respective word of the product reviews associated with the product is associated with a value-sensitive description. 
 
     
     
         13 . The method of  claim 11 , wherein generating the probability further comprises using a hill climbing algorithm. 
     
     
         14 . The method of  claim 11 , wherein identifying the segment of the users further comprises identifying first users and second users, wherein the second users are not value conscious about the product. 
     
     
         15 . The method of  claim 14  further comprising:
 analyzing shopping histories of the first users and the second users; and 
 analyzing shopping patterns of the first users and the second users. 
 
     
     
         16 . The method of  claim 15 , wherein analyzing the shopping patterns for the first users and the second users further comprises:
 analyzing on-line shopping patterns for the first users and the second users, wherein the on-line shopping patterns further comprise at least one of:
 a user purchase history; 
 a user browser activity; 
 a user value conscious webpage visit; or 
 a user profile. 
   
     
     
         17 . The method of  claim 16  further comprising:
 leveraging low-rank matrices to infer additional latent features for the first users, the second users, and one or more products to leverage low-rank matrices; and 
 calculating, using matrix factorization, a behavior of the first users and the second users associated with products that are co-bought. 
 
     
     
         18 . The method of  claim 11 , wherein transmitting the instructions to display the recommendation for the product further comprises transmitting instructions to update a respective webpage of a website displaying a value-sensitive product. 
     
     
         19 . The method of  claim 11  further comprising:
 preparing a first recommendation and a first promotion for the product; and 
 preparing a second recommendation and a second promotion for the product; 
 preparing the first recommendation and the first promotion comprises preparing larger discounts and savings for the first recommendation and the first promotion than for the second recommendation and the second promotion; and 
 preparing the second recommendation and the second promotion comprises preparing discounts and savings for the second recommendation and the second promotion based on descriptions in user profiles of second users comprising at least one of age, family size, pets, hobbies, geographic location, or gender. 
 
     
     
         20 . The method of  claim 19  further comprising:
 determining whether to display the first recommendation and the first promotion for the product to first users; and 
 determining whether to display the second recommendation and the second promotion for the product to the second users based on user profiles of the second users.