报告题目：Machine Learning Approach to MeanReversion Trading

报告时间：2022-03-24 10:00-12:00          

报告地点：ZOOM（ID：878 7426 3432；口令：150522）

链 接：https://us02web.zoom.us/j/87874263432

组织单位：北京大学数学科学学院

报告摘要：

We discuss a practical machinelearning approach to construct portfolios with mean-reverting price dynamics.Our objectives are threefold: (1) design a portfolio that is well-representedby a mean-reverting process with parameters estimated by maximum likelihood,(2) select portfolios with desirable characteristics, such as high meanreversion, and (3) build a parsimonious portfolio, i.e. find a small subsetfrom a larger collection of assets for long/short positions. Our data-drivenmethod combines statistical learning and optimization. We present a specializedprojected gradient algorithm to solve the constrained non-convex problemembedded in the trading problem. Numerical examples using empirical price dataare provided.

报告人简介：

Tim Leung is the Boeing EndowedChair Professor in the Department of Applied Mathematics and the Director ofthe Computational Finance & Risk Management (CFRM) program and QuantitativeAnalytics Lab at University of Washington in Seattle. He has previously taughtin the Department of Applied Mathematics & Statistics at Johns HopkinsUniversity and in the Department of Industrial Engineering & OperationsResearch at Columbia University. He obtained his BS from Cornell University andPhD from Princeton University. His research in Quantitative Finance has beenfunded by the National Science Foundation (NSF). He has published over 70peer-reviewed articles and several books on the topics of Mean ReversionTrading, ETFs, and more. Professor Leung is on the advisory board of the AI forFinance Institute and the editorial board of multiple journals. He has servedas the Chair for the INFORMS Finance Section as well as the Vice Chair for theSIAM Activity Group on Financial Mathematics & Engineering.