Mining shopping data with passive tags via velocity analysis

摘要

Unlikeonline shopping, it is difficult for the physical store to collect customer shopping data during the process of shopping and conduct in-depth data mining. The existing methods to solve this problem only considered how to collect and analyze the data, but they have not paid attention to the large computation amount, bulk data amount, and long time delay, in which they can not feedback user data timely and effectively. In this paper, we present the received signal strength of passive radio frequency identification (RFID) tags that can be used to carry out on-site shopping data mining, such as which items are popular, which goods are customers interested in, which items are usually bought together, which areas have a large customer flow, and what is the order of items being bought by customers. By exploiting the received signal strength indicator (RSSI) information, we calculate the velocity of the items and then leverage machine learning and hierarchical agglomerative clustering to carry out in-depth analysis of velocity data. We implement a prototype in which all components are built by off-the-shelf devices. Meanwhile, we conduct extensive experiments in the real environment. The experiment results show that our methods have low computation and latency, which demonstrate that our proposed system is quite feasible in practical shopping data analysis.