FINTECH THRUST SEMINAR | Illusion of Stock Return Predictability
Supporting the below United Nations Sustainable Development Goals:支持以下聯合國可持續發展目標：支持以下联合国可持续发展目标：
Illusion of Stock Return Predictability
Abstract:
There is extensive literature on individual stock return predictability in the cross section and time series, but it mostly examines the aggregate performance by ignoring the heterogeneous stock return predictability. This paper challenges the existence of aggregate predictability by investigating heterogeneous stock return predictability on high-dimensional characteristics and macroeconomic predictors. We develop a tree-based asset clustering approach to partition the panel of stock-return observations in the cross section and/or time series for differentiating their predictability difference. Studying U.S. equity for the recent five decades, we find some characteristics-based or macro-based clusters are more predictable, which is further linked to higher risk-adjusted investment performance and risk anomalies.
Guanhao (Gavin) Feng is an assistant professor of business statistics at the City University of Hong Kong and a scientist in the Lab for AI-Powered FinTech. His publications have appeared in prestigious journals such as the Journal of Finance, Journal of Financial and Quantitative Analysis, Journal of Econometrics, and International Economic Review. He is the PI for several research grants, including the HKRGC ECS and GRF grants, as well as the NSFC youth scientist fund. Gavin’s research has also received recognition through industry awards, including the AQR Insight Award (1st prize), Crowell Prize (2nd prize), and PwC 3535 Finance Forum Annual Best Paper Award.
Gavin earned his Ph.D. and MBA from the University of Chicago in 2017. His research interests cover Bayesian statistics, empirical asset pricing, machine learning in finance, and time-varying econometrics.