讲座：A scalable recommendation engine for new users and items 发布时间：2023-10-09
题 目：A scalable recommendation engine for new users and items
嘉 宾：Boya Xu（许博雅）, Ph.D. Candidate, Duke University
主持人：张铄 副教授 国产超高效液相色谱
地 点：上海交通大学 徐汇校区 安泰经济与管理学院A303
In many digital contexts such as online news and e-tailing with many new users and items, recommendation systems face several challenges: i) how to make initial recommendations to users with little or no response history (i.e., cold-start problem), ii) how to learn user preferences on items (test and learn), and iii) how to scale across many users and items with myriad demographics and attributes. While many recommendation systems accommodate aspects of these challenges, few if any address all. This paper introduces a Collaborative Filtering (CF) Multi-armed Bandit (B) with Attributes (A) recommendation system (CFB-A) to jointly accommodate all of these considerations. Empirical applications including an offline test on MovieLens data, synthetic data simulations, and an online grocery experiment indicate the CFB-A leads to substantial improvement on cumulative average rewards (e.g., total money or time spent, clicks, purchased quantities, average ratings, etc.) relative to the most powerful extant baseline methods.
Boya Xu is a Ph.D. candidate at Duke University’s Fuqua School of Business. Her research explores the influential factors shaping the new content generation on social media, examines the causal effects of social media publicity on local entrepreneurs' adoption of new technology, and develops recommendation algorithms to distribute new products at scale in a two-sided market. To do so, she uses a collection of methodologies from machine learning, online experimentation, and causal inference. In summary, her research aims to inform and optimize platform stakeholders’ marketing strategies by considering the innovation dynamics including generation, adoption, and distribution.
Boya Xu is the 2023 AMA Sheth Foundation Doctoral Consortium Fellow, and the 2021 and 2023 INFORMS Marketing Science Doctoral Consortium Fellow.
Prior to joining the doctoral program at Duke University, Boya Xu received her BS in Statistics from Zhejiang University and my MA in Economics from Duke University.