报告题目：Distributionally robust optimization with Wasserstein metric for multi-period portfolio selection under uncertainty

报告人：吴中明 副教授 南京信息工程大学

邀请人：赵志华

报告时间：2023年6月9日（周五）下午2:30-5:30

腾讯会议ID：758-171-592

报告人简介：吴中明，南京信息工程大学副教授，香港中文大学博士后。主持国家自科青年基金项目和中国博士后面上资助项目，入选江苏省“双创博士”和人社部“香江学者”。担任中国运筹学会宣委会执行委员、中国运筹学会数学规划分会青年理事、江苏省运筹学会副秘书长、理事。研究方向为最优化理论、算法及其应用，在Computational Optimization and Applications、Journal of Global Optimization、Journal of Optimization Theory and Applications、Mathematics of Computation、 IEEE Transactions on Signal Processing、IEEE Transactions on Instrumentation and Measurement、系统工程理论与实践等期刊发表论文二十余篇。

报告摘要：The mean-variance model formulated by Markowitz for a single period serves as a fundamental method of modern portfolio selection. In this study, we consider a multi-period case with uncertainty that better matches the reality of the financial market. Using the Wasserstein metric to characterize the uncertainty of returns in each period, a new distributionally robust mean-variance model is proposed to solve multi-period portfolio selection problem. We further transform the developed model into a tractable convex problem using duality theory. We also apply a nonparametric bootstrap method and provide a specific algorithm to estimate the radius of the Wasserstein ball. The effects of the parameters on the corresponding strategy and evaluation criteria of portfolios are analyzed using in-sample data. The analysis indicate that the return and risk of our portfolio selections are relatively immune to parameter values. Finally, a series of out-of-sample experiments demonstrate that the proposed model is superior to some other models in terms of final wealth, standard deviation, and Sharpe ratio.