管理科学与工程系学术论坛第八十五讲

主 题：Personalized Promotion Recommendation through Consumer Evolution Modeling

主讲人: 王聪（清华大学经济管理学院管理科学与工程专业博士研究生）

时 间：2019-01-11 12:30

地 点：明德商学楼712室

语 言：英文

Recent years have witnessed the great passion of shoppers to purchase products at promotion, leading to "smarter" consumers with growing price sensitivity towards promotion. In order to provide personalized promotion recommendations to the more price sensitive consumers, it is critical to take account of the temporal dynamics of preference and price sensitivity simultaneously in recommender systems. Although consumer preference has been richly studied in recommender systems, little attention has been paid to exploring consumers' growing price sensitivity. In this study, we seek to bridge the gap by modeling the temporal dynamics of consumer preference and price sensitivity simultaneously through the lens of consumer experience evolution. Given the commonly implicit nature of consumer behavior, a pairwise learning framework based on matrix factorization and Bayesian personalized ranking, i.e., exFBPR is proposed and a new sampling strategy tailored for multiple feedbacks is developed accordingly. Furthermore, extensive empirical experiments have been conducted on two real-world datasets. Both quantitative and qualitative results indicate the proposed framework is superior to state-of-the-art methods in providing satisfying personalized promotion recommendations and can be applied to obtain business insights of consumer behavior.