Yi Fang received $30,000 from DOCOMO Innovations, Inc.
Yi Fang with the Computer Science and Engineering Dept. has received a $30,000 from DOCOMO Innovations, Inc. Funds will be used to support his project "Neural Learning to Rank for Sequential Recommendation Systems."
Recommendation systems are a core part of many online services that we use every day, from video recommendations on YouTube to shopping items on Amazon. Accurately characterizing user preferences lives at the heart of an effective recommendation system. In many real-world applications, users' current interests are intrinsically dynamic and evolving, influenced by their historical behaviors. In this project, we aim at modeling sequential dynamics in user behaviors to make sequential recommendations based on users' historical interactions. We seek to propose novel neural learning to rank techniques to learn the representations for users' historical behavior sequences. Inspired by the success of BERT in text understanding, we will explore the deep bidirectional self-attention model to sequential recommendation.