Edge weight based computer models for item recommendation

A system for item recommendation, the system comprising:

• a memory storing an item recommendation model trained using dense representations for a set of items for sale in a retail facility, the dense representations generated based on an item interaction graph comprising nodes corresponding to the set of items for sale in a retail facility, edges connecting the nodes, and edge weights for the edges, wherein the edge weights are related to item selection sequence of the set of items for sale in the retail facility, the item interaction graph generated at least by:
• assigning each of the set of items for sale in the retail facility to each of the nodes;
• connecting, with an edge, two nodes corresponding to two items selected for a shopping cart;
• and
• calculating, based on the item selection sequence of the two items, an edge weight for the edge;
• and
• a control circuit coupled to the memory, the control circuit configured to:
• receive an indication of an item selection by a user in the retail facility;
• generate a recommendation for a suggested next item based on using the item selection as an input of the item recommendation model;
• cause the suggested next item to be presented to the user for potential selection;
• transmit, for storage in an edge device executing a shopping application, the item recommendation model;
• monitor an online traffic of a backend system;
• and
• cause, in response to detection of the online traffic higher than a threshold value, the shopping application executed on the edge device to generate, using the item recommendation model stored in the edge device, a recommendation for a suggested next item for display on a graphical user interface of the shopping application for a customer to consider selecting.