Mining shopping data with passive RFID tags
The uses of passive RFID tags to find out which items are popular, which items are bought together and what order items are being bought by customers.
Unlike online shopping, it is difficult for physical stores to collect customer shopping data during the process of shopping and conduct in-depth data mining. In a study recently published in EURASIP Journal on Wireless Communications and Networking, researchers 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, researchers calculated the velocity of the items and then leveraged machine learning and a method of analysis called hierarchical agglomerative clustering to carry out in-depth analysis of velocity data. The researchers then implemented a prototype in which all components are built by off-the-shelf devices. They are conducting extensive experiments in the real environment.