Making Recommendations Better: The Role of User Online Purchase Intention Identification
Kuan Fang, Qi Zhang, Zhuoran Zhuang, Zi‐Ke Zhang · 2016
The past few years has witnessed the great success of recommender systems, which can significantly help users find relevant and interesting items from the vast array of online products. Recently, a vast class of researches in this area mainly focus on making recommendations by designing effective algorithms. Comparatively, the user intention, especially the role of purchase intention in recommender systems is relatively lack of study. In this paper, with real e-commercial data from Tmall.com, we firstly analyze users' online behaviors and propose a scenario-based identification approach to classify users into two groups: one with obvious purchase intention, and another without such motivation. We then use Random Forest classification method to validate its usefulness. Subsequently, we implement an online demo to visually detect the real-time purchase intention. Finally, we employ the classical item-based collaborative filtering framework to provide recommendations to those two group users. Experimental results show that recommendation performance indeed can be enhanced by identifying online purchase intention.