Systems and methods for automatically recommending an item to a customer while shopping at a retail store

Abstract

In some embodiments, apparatuses and methods are provided herein useful to automatically recommending an item. In some embodiments, there is provided a system for automatically recommending an item to a customer comprising a plurality of items available for purchase; and a control circuit configured to determine information associated with a first item of the plurality of items selected by a user; identify one or more items previously purchased by the user that are located within a threshold proximity; determine a most frequently bought item of the identified one or more items; and cause display on an electronic device of a suggestion for the user to collect the most frequently bought item.

What is claimed is: 
     
         1 . A system for automatically recommending an item to a customer while the customer is shopping at a retailer, the system comprising:
 a plurality of items available for purchase at the retailer;   an application associated with the retailer and operable with an electronic device associated with a user that is shopping at the retailer, the electronic device in cooperation with the application configured to obtain identifying data corresponding to a first item collected by the user for purchase while the user is shopping at the retailer; and   a control circuit communicatively coupled to the application via a network, the control circuit configured to:
 determine information associated with the first item of the plurality of items selected by the user; 
 identify one or more items previously purchased by the user that are within a threshold proximity to a location associated with the first item based on a stored user profile; 
 determine, using a trained machine learning model, a most frequently bought item of the identified one or more items previously purchased by the user; 
 cause display on the electronic device of a suggestion for the user to collect the most frequently bought item; 
 update the stored user profile when the user purchases the most frequently bought item, wherein the trained machine learning model bases a subsequent determination of the most frequently bought item to be suggested to the user on the updated stored user profile; and 
 update the threshold proximity used in the subsequent determination of the most frequently bought item suggested to the user based on a historical pattern over a period of time of a failure to cause the user to purchase the most frequently bought item. 
   
     
     
         2 . The system of  claim 1 , wherein the threshold proximity is based on a historical pattern over a period of time of suggesting the most frequently bought item that is subsequently purchased by the user prior to leaving the retailer. 
     
     
         3 . The system of  claim 1 , wherein the update of the threshold proximity corresponds to increasing the threshold proximity. 
     
     
         4 . The system of  claim 1 , wherein the control circuit is further configured to:
 receive initiation signal from the electronic device when the user enters the retailer to enable the control circuit to determine whether the user has previously purchased items at the retailer, wherein the initiation signal comprises one or more user attributes and location data of the electronic device; and   in response to the receipt of the initiation signal, provide a store identifier associated with the retailer to the electronic device, and wherein the store identifier is stored by the electronic device.   
     
     
         5 . The system of  claim 4 , wherein data received by the control circuit in response to obtaining the identifying data corresponding to the first item by the electronic device comprises an item identifier associated with the first item and the store identifier associated with the retailer. 
     
     
         6 . The system of  claim 1 , wherein the trained machine learning model is trained to determine an item previously purchased by the user that is within a threshold of probability of likelihood of being selected by the user when presented to the user based on the stored user profile. 
     
     
         7 . A system for automatically recommending an item to a customer while the customer is shopping at a retailer, the system comprising:
 a plurality of items available for purchase at the retailer;   an application associated with the retailer and operable with an electronic device associated with a user that is shopping at the retailer, the electronic device in cooperation with the application configured to obtain identifying data corresponding to a first item collected by the user for purchase while the user is shopping at the retailer; and   a control circuit communicatively coupled to the application via a network, the control circuit configured to:
 determine information associated with the first item of the plurality of items selected by the user; 
 identify one or more items previously purchased by the user that are within a threshold proximity to a location associated with the first item based on a stored user profile; 
 determine, using a trained machine learning model, a most frequently bought item of the identified one or more items previously purchased by the user; 
 cause display on the electronic device of a suggestion for the user to collect the most frequently bought item; and 
 update the stored user profile when the user purchases the most frequently bought item, wherein the trained machine learning model bases a subsequent determination of the most frequently bought item the updated stored user profile; 
 wherein, in an event that the determination of the most frequently bought item results in determining a number of items that are most frequently bought, the control circuit is further configured to:
 determine, using the trained machine learning model, a highest weighted one of the number of items that are most frequently bought relative to weighting values associated with remaining number of items, wherein each of the weighting values is based on corresponding item attributes, item-user interaction attributes, and user attributes; and 
 trigger display on the electronic device of a second suggestion for the user to collect the highest weighted one of the number of items and add the highest weighted one of the number of items to an electronic shopping list of items to purchase. 
 
   
     
     
         8 . The system of  claim 7 , wherein the item-user interaction attributes comprise a number of times the user purchased, touched, and searched the most frequently bought item. 
     
     
         9 . The system of  claim 7 , wherein the threshold proximity is based on a historical pattern over a period of time of suggesting the most frequently bought item that is subsequently purchased by the user prior to leaving the retailer. 
     
     
         10 . The system of  claim 7 , wherein the control circuit is further configured to increase the threshold proximity based on a historical pattern over a period of time of a failure to cause the user to purchase the most frequently bought item prior to leaving the retailer after the suggestion. 
     
     
         11 . The system of  claim 7 , wherein the control circuit is further configured to:
 receive initiation signal from the electronic device when the user enters the retailer to enable the control circuit to determine whether the user has previously purchased items at the retailer, wherein the initiation signal comprises one or more user attributes and location data of the electronic device; and   in response to the receipt of the initiation signal, provide a store identifier associated with the retailer to the electronic device, and wherein the store identifier is stored by the electronic device.   
     
     
         12 . The system of  claim 11 , wherein data received by the control circuit in response to obtaining the identifying data corresponding to the first item by the electronic device comprises an item identifier associated with the first item and the store identifier associated with the retailer. 
     
     
         13 . The system of  claim 7 , wherein the trained machine learning model is trained to determine an item previously purchased by the user that is within a threshold of probability of likelihood of being selected by the user when presented to the user based on the stored user profile. 
     
     
         14 . A system for automatically recommending an item to a customer while the customer is shopping at a retailer, the system comprising:
 a plurality of items available for purchase at the retailer;   an application associated with the retailer and operable with an electronic device associated with a user that is shopping at the retailer, the electronic device in cooperation with the application configured to obtain identifying data corresponding to a first item collected by the user for purchase while the user is shopping at the retailer; and   a control circuit communicatively coupled to the application via a network, the control circuit configured to:
 determine information associated with the first item of the plurality of items selected by the user; 
 identify one or more items previously purchased by the user that are within a threshold proximity to a location associated with the first item based on a stored user profile; 
 determine, using a trained machine learning model, a most frequently bought item of the identified one or more items previously purchased by the user; 
 cause display on the electronic device of a suggestion for the user to collect the most frequently bought item; 
 update the stored user profile when the user purchases the most frequently bought item, wherein the trained machine learning model bases a subsequent determination of the most frequently bought item to be suggested to the user on the updated stored user profile; and 
 in response to a determination that the user has not previously purchased any one item of the plurality of items at the retailer, identify a second item of the plurality of items based on the second item being associated with at least one of a plurality of prioritized-product types, the second item being associated with a highest weighting value relative to weighting values of other items associated with the same prioritized-product type associated with the second item, and the second item being located within the threshold proximity to the location of the first item. 
   
     
     
         15 . The system of  claim 14 , wherein the plurality of prioritized-product types comprises a holiday sales item, an instant saving item, a private brand item, a top seller item, and a seasonal item. 
     
     
         16 . The system of  claim 15 , wherein each of the plurality of prioritized-product types is ranked relative to one another. 
     
     
         17 . The system of  claim 14 , wherein the threshold proximity is based on a historical pattern over a period of time of suggesting the most frequently bought item that is subsequently purchased by the user prior to leaving the retailer. 
     
     
         18 . The system of  claim 14 , wherein the control circuit is further configured to increase the threshold proximity based on a historical pattern over a period of time of a failure to cause the user to purchase the most frequently bought item prior to leaving the retailer after the suggestion. 
     
     
         19 . The system of  claim 14 , wherein the control circuit is further configured to:
 receive initiation signal from the electronic device when the user enters the retailer to enable the control circuit to determine whether the user has previously purchased items at the retailer, wherein the initiation signal comprises one or more user attributes and location data of the electronic device; and   in response to the receipt of the initiation signal, provide a store identifier associated with the retailer to the electronic device, and wherein the store identifier is stored by the electronic device.   
     
     
         20 . The system of  claim 14 , wherein the trained machine learning model is trained to determine an item previously purchased by the user that is within a threshold of probability of likelihood of being selected by the user when presented to the user based on the stored user profile.