Shopping Path Analysis and Transaction Mining Based on RFID Technology

Abstract

The RFID technology is gaining strong support from business for various applications such as supply chain management, access control, airline luggage management, etc. Due to the cost consideration, it is still not a replacement for the traditional item-level bar code. Therefore, tracking and analyzing the shopping paths and purchasing behaviors of customers in a superstore such as Wal-Mart is still a challenging task. In this paper, we propose a RFID deployment model for collecting shopping paths and purchased items of customers. Algorithms based on customer access matrix (CAM) and customer transaction mining (CTM) are then proposed for mining preferred shopping paths and their relationships to the purchased items. In the experiments, we build a dataset generator for generating shopping paths and purchased items of customers, and the results show that our model is applicable to real applications.