Abstract: Systems herein allow a store to make store-specific product recommendations to customers who are in the store. The system builds a graph database of relationships between products based on sales data, such as invoices. The relationships are stored as edges with store-specific edge values. Store similarities are determined by a genetic algorithm that creates a candidate solution that includes an array of weights for each store, representing that store's similarity with the other stores. The system includes a recommendation engine that receives a recommendation request identifying a target store and a target product. Based on that, the corresponding edges are retrieved, the edge values are weighted based on the candidate solution, and the highest-weighted connected products are recommended.

Abstract: A system can include a tap wall that has multiple screens for display product images to customers. The tap wall can be populated by a server. The tap wall can prompt a user to visit an address on their user device. The address can direct the user device to the server, allowing the server to open a socket communication with both the user device and the tap wall. The server can access a first party cookie on the user device and display products on the tap wall based on products associated with the first party cookie. A user can build a collection of products both in-store and out-of-store that get associates with the cookie. The user can remain anonymous while the system does makes relevant product recommendations on the tap wall based on the user's entire browsing experience.