Out-of-Sample Sharpe Estimation and Volatility Proxy Construction
Chinese Title（样本外夏普比率估计与波动率鲁棒代理构造）
主讲人：
Weichen Wang（The University of Hong Kong）
主持老师：
（北大经院）王一鸣、王法
参与老师：
（北大经院）王熙、刘蕴霆、巩爱博
时间：
2025年12月5日（周五）
10:00-11:30
地点（线下）：
北京大学经济学院107会议室
主讲人简介：
Prof Weichen Wang joined The University of Hong Kong in 2021 as an Assistant Professor in the area of Innovation and Information Management of HKU Business School. Weichen obtained his PhD in Operations Research and Financial Engineering from Princeton University in 2016, supervised by Prof Jianqing Fan. After graduation, Weichen joined Two Sigma Investments as a quantitative researcher. He also served as a visiting lecturer at Princeton University for Spring 2020. Before PhD, Weichen received his bachelor’s degree in Mathematics and Physics from Tsinghua University in 2011. Prof Wang’s research combine statistics, econometrics and machine learning techniques, and find applications in portfolio management and financial science. He is particularly interested in the factor structure of the financial market and real-world applications of machine learning. His works have been published in Annals of Statistics, Journal of the American Statistical Association, Journal of Machine Learning Research, Journal of Econometrics, Operations Research etc.
报告摘要：
This talk will contain two parts. The first half is about estimation of out-of-sample Sharpe ratio for high dimensional portfolio optimization, and the second half is about an empirical deviation perspective on volatility proxy construction.
Portfolio optimization aims at constructing a realistic portfolio with significant out-of-sample performance, typically measured by the out-of-sample Sharpe ratio. However, due to in-sample optimism, it is inappropriate to use the in-sample estimated covariance to evaluate the out-of-sample Sharpe, especially in the high dimensional settings. We propose a novel method to estimate the out-of-sample Sharpe ratio using only in-sample data, based on random matrix theory. Furthermore, portfolio managers can use the estimated out-of-sample Sharpe as a criterion to decide the best tuning for constructing their portfolios. We demonstrate the effectiveness of our approach through comprehensive simulations and real data experiments.
Volatility forecasting is crucial to risk management and portfolio construction. One particular challenge of assessing volatility forecasts is how to construct a robust proxy for the unknown true volatility. In this talk, we show that the empirical loss comparison between two volatility predictors hinges on the deviation of the volatility proxy from the true volatility. We then establish non-asymptotic deviation bounds for three robust volatility proxies, two of which are based on clipped data, and the third of which is based on exponentially weighted Huber loss minimization. Finally, we exploit the proposed robust volatility proxy to compare different volatility predictors on the Bitcoin market data. When the sample size is limited, applying the robust volatility proxy gives more consistent and stable evaluation of volatility forecasts.
