时 间：2024年12月25日 10:00 - 11:00
地 点：普陀校区理科大楼A1714
报告人：曾旭东 上海财经大学教授
主持人：李丹萍 华东师范大学教授
摘 要：
The identification of an optimal portfolio strategy becomes challenging when true parameters are unknown and estimation errors are present. To address this issue, we introduce a novel framework that consistently enhances the out-of-sample performance of any given portfolio. This framework constructs an "orthogonal" portfolio relative to the original one, followed by an optimal combination of the two. Analytical results show that this combined portfolio can consistently outperform the original portfolio in terms of certainty equivalent return (CER). Additionally, we propose an iterative algorithm to obtain better and better portfolios, and we prove such an iteration procedure converges under moderate conditions. Results from both simulated and real datasets show significant improvements in out-of-sample performance using our approach.
报告人简介：
曾旭东，南加州大学金融数学博士，现任上海财经大学金融学院教授，博士生导师，保险系主任，金融科技研究中心主任。研究方向包括保险科技，投资组合，金融资产定价，风险管理等。已在Journal of Economic Theory, Management Science，Insurance: Mathematics and Economics, 管理科学学报等金融学、管理学和风险管理研究领域国际顶尖学术期刊上发表论文数十篇。主持两项国家基金项目，一项教育部人文社科重点研究基地重大项目。