Prof. FENG Guanhao from the City University of Hong Kong gave a seminar at our department
Date: 2018-01-23

Prof. FENG Guanhao from the City University of Hong Kong gave a seminar at 315 meeting room, the 3rd building of Wisdom park of South University of Science and Technology of China on 18th Sept 2018. The topic is “Deep learning Factor Alpha”. In this seminar, Prof. Feng gave a speech firstly demonstrating the phenomena that how high-dimensional firm characteristics affect the average return of those stocks. Additionally, He illustrated a deep learning automated solution to generate risk factors and its relevant empirical results. By using deep neural network, his algorithm performs a multiple nonlinear transformation of firms’ characteristics, which is then used for security sorting of investment portfolio. Eventually, it generates long-short portfolios as risk factors, which are also named Deep Learning Factors. Compared to traditional investment benchmarked factors, such as SMB and HML from the Fama-French three factors model, Deep Learning Factors provide a better out-of-sample performance in empirical asset pricing tests. In particular, it can minimize the average squared alpha from test portfolios.


Prof. FENG Guanhao from the City University of Hong Kong gave a seminar at our department


    FENG Guanhao is an assistant Professor at the Department of Management Science, College of Business, the City University of Hong Kong. He received his Ph.D. in Econometrics and Statistics from University of Chicago and joined City U as an assistant professor of statistics in 2017. He has worked as a quantitative researcher intern at Citadel for machine learning research. Prof. FENG’s research interests include financial time series, empirical asset pricing, machine learning, and quantitative finance. His work on taming the factor zoo in asset pricing earned the 2018 AQR Insight Award. Additionally, his work on deep learning asset pricing was awarded by the Unigestion Alternative Risk Premia Research Academy.