Characterizing the Spatial Association Between Retail Hotspots Based on Sensor Data

The Retail industry is being heavily disrupted by technology such as IoT, and the spread of smart phones sensor technologies which creates infinite possibilities specially for merchants to figure out their customers actions and habits while visiting their shops. This gives sights on how to enhance the customers shopping experiences. In this paper, we present an IoT multi-model sensors approach for detecting the shoppers behaviour and present the best or worst shoppers experiences as `Hot or Cold Spots'. We seize customers shopping habits by utilising continuous smart phone sensor data collection method using wearable and ecological sensors. The data is labeled with the users rating, location, time stamp and the order of the shoppers visits round the stores. The approach proposes the use of GetisOrd (Gi*) spatial statistics to identify hot spots on shopping areas from the collected data sets allowing to spatially compare data clusters in relation to customers behaviour. This study allows us to observe how mobile sensing unveils the characteristics of places from such crowd -contributed content for many benefits such as real estate valuation, sales comparison, advertising for income capitalisation and to increase customers satisfactions.