User behaviour modeling, recommendations, and purchase prediction during shopping festivals

Abstract

This work investigates user online browsing and purchasing behaviors, and predicts purchasing actions during a large shopping festival in China. To improve online shopping experience for consumers, increase sales for merchants and achieve effective warehousing and delivery, we first analyse diverse online shopping behaviours based on the 31 million logs generated accompanied with online shopping during a rushed sale event on 11st November, 2016. Based on the obtained user behaviours and massive data, we apply collaborative filtering based method to recommend items for different consumers, and predict whether purchase will happen. We conduct 5-fold cross validation to evaluate the collaborative filtering based recommendation method, and further identify the critical shopping behaviors that determine the precursors of purchases. As online shopping becomes a global phenomenon, findings in this study have implications on both shopping experience and sales enhancement.