User Novelty Driven Personalized Item Recommendation

Abstract

Temporal item recommendation is crucial for many online personalized services such as music and location recommendation. Meanwhile, user novelty measures how much the active user is willing to accept unfamiliar things in real time. The main topic of this talk is about how AI technologies can be applied to analyze user novelty and further facilitate the improvement of personalized temporal item recommendation.

Biography

Dr. Jun Chen holds a Ph.D. degree and a B.Eng. degree in Software Engineering both from Tsinghua University. He has broad research interests in machine learning and data mining, especially in recommender systems. His first-authored research papers have been published in the top ranked venues like IEEE TKDE, IEEE TIP, AAAI, ACM Multimedia and KAIS. In 2017, he has won the outstanding Ph.D. graduate of Tsinghua University and that of Beijing city as well as the outstanding Ph.D. dissertation of Tsinghua University.