A Framework of Recommendation System Based on In-store Behavior
Wai Tik So, Katsutoshi Yada · 2017
Due to the development of ecommerce, recommendation systems are becoming increasingly common in daily life, and essential for business. Most conventional recommendation systems are based on purchase frequency obtained from sales data. We found no system based on similarity of purchase processes, like customers' in-store behavior. Therefore, we propose a recommendation system based on similarity of staying time obtained from the customer's shopping path data, and compare its performance vs. a recommendation system based on purchase frequency. This paper clarified that the proposed system has higher performance than a system based on purchase frequency.