Understanding customer behaviour in urban shopping mall from WiFi logs

Traditional ways of understanding customer behaviour are mainly based on predominantly field surveys, which are not effective as they require labor-intensive survey. As mobile devices and ubiquitous sensing technologies are becoming more and more pervasive, user-generated data from these platforms are providing rich information to uncover customer preference. In this study, we propose a shop recommendation model for urban shopping mall by exploiting user-generated WiFi logs to learn customer preference. Specifically, the proposed model consists of two phases: 1) offline learning customer's preference from their check-in activities; 2) online recommendation by fusing the learnt preference and temporal influence. We have performed a comprehensive experiment evaluation on a real dataset collected by over 39,000 customers during 7 months, and the experiment results show the proposed recommendation model outperforms state-of-the-art methods.