Development of consumers management system via face classification

Abstract

To improve consumer experience and overall retail management, physical retailers may adapt consumer behaviour management systems using artificial intelligence to imitate the capability of consumer behaviour tracking in online shopping into physical retail. The proposed consumer behaviour management system consists of two parts - face recognition and consumer tracking at an area of interest. Both will be combined to produce a summary of individual customer’s visits to the shop. This information can be used to improve consumers experience and optimize retailer’s management. The developed system can track consumers’ movement inside the shop and summarize their whereabouts according to areas of interest. The face classification system via FaceNet has around 56.67% accuracy with 27.89% mean confidence. The tracking performance shows a consistent performance with a total standard deviation of 4.36 seconds. With the consumers’ analysis graph, retailers may pinpoint which area that was always frequented by their customers and take suitable actions with that information.