How Do Customers Buy Them at a Supermarket? Behavior Analysis from Real Observation and Agent Simulation

This paper presents a customer behavioral model for grounding the number of purchase items in Agent-Based In-Store Simulator (ABISS). ABISS is a decision support system for a retail management. Using ABISS, we are able to virtually investigate the shopping paths of the customers and analyze the effect of sales promotion. To grounding the number of purchase items, first we conduct a field study using Radio Frequency Identification (RFID) and analyze the collected RFID data and Point-of-Sales (POS) data. Then we develop a decision model, which determined customers’ “Shopping List”, “Possession Money Limit”, and “Staying time”. The experimental result has revealed that we ground the number of purchasing items of obtained by the POS data, if we concentrate on the tuning of ABISS parameters on “Shopping List” and “Possession Money Limit”.