Design and Implementation an RFID Customer Shopping Behaviour Mining System

Abstract

Shopping behavior data is of great an importance in understanding the effectiveness of marketing and merchandising campaigns. Online clothing stores are capable of the capturing customer shopping behavior by analyzing the click streams and customer shopping carts. Retailers within physical clothing stores, however, still lack effective methods to comprehensively identify shopping behaviors. In this study, we show that backscatter signals of passive RFID tags can be exploited to detect and record how customers browse stores, which garments they pay attention to, and which garments they usually pair up. The intuition is that phase readings of tags attached to items will demonstrate distinct yet stable patterns in a time-series when customers look at, pick out, or turn over desired items. We design Shop Miner, a framework that harnesses these unique spatial-temporal correlations of time-series phase readings to detect comprehensive shopping behaviors. We have implemented a prototype of Shop Miner with a COTS RFID reader and four antennas, and tested its effectiveness in two typical indoor environments. Empirical studies from two-week shopping-like data show that Shop Miner is able to identify customer shopping behaviors with high accuracy and low overhead, and is robust to interference.