Topic：A Dynamic Multi-strategy using a Constrained Sparse Penalized Regression Analysis of Combinations of Notorious Portfolios with Reinforcement Learning
Speaker： Bertrand Maillet, Senior Researcher at the School of Economics, Ca' Foscari University of Venice, and Full Professor of Financial Economics at the University of Saint-Denis - La Réunion
Host: Professor Zhang Xiang, Deputy Director of Domestic Cooperation and Development Office
Time：May 29, 15:00—16:30
Location: Room 618A, Gezhi Building
Organizers：School of Finance，Institute of Chinese Financial Studies, Research Office
Speaker’s Profile:
Professor Bertrand Maillet, a Senior Researcher at the School of Economics, Ca' Foscari University of Venice (Università Ca' Foscari Venezia), and a Full Professor of Financial Economics at the University of Saint Denis - La Réunion, France, holds a distinguished profile in academia. His research interests encompass a broad spectrum including financial economics, econometrics, risk management, performance evaluation, portfolio management, systemic risk, machine learning, ESG (Environmental, Social, and Governance) and green finance, as well as asset pricing.
In the past five years, Professor Maillet has published numerous papers in prestigious journals such as the Journal of Banking & Finance, European Journal of Operational Research, Annals of Operations Research, and Computational Economics, among others. These publications delve into pivotal topics within financial economics, ranging from financial networks, asset pricing, and machine learning to systemic risk and performance assessment relating to investor characteristics and investment behaviors. Moreover, Professor Maillet has made significant contributions in the realm of asset allocation and pricing models, evidenced by his notable publication, "Multi-moment Asset Allocation and Pricing Models," issued by John Wiley & Sons, NYC.
Lecture Preview：
The Mean-Variance model is a widely used asset allocation model in finance, both in academia and industry. In this article, we provide another perspective. The key insight is to take advantage of previous research articles and related solutions, and to put them into the statistical framework of the original approach, complemented by ideas coming from the machine learning field. This insight allows us to significantly improve computational simplicity, computing efficiency, explanatory power and, finally, robustness of optimal portfolios of the Mean-Variance model. We thus propose an innovative approach to dynamic multi-strategy asset allocation, wherein we synergistically combine various influential “notorious portfolios” previously introduced in the financial literature. By harnessing a Reinforcement Learning technique and its adaptable intrinsic nature, our methodology aims to empower fund performance in the long-term, while accommodating diverse real market constraints. Through extensive empirical investigations encompassing a comprehensive gamut of numerous pivotal portfolios, we show the efficacy of our proposed method in diverse market conditions, thus surpassing existing benchmarks and strategies deemed state-of-the-art. Notably, our approach consistently delivers superior performance and lower risk, then outperforming competing methods across various market periods and stock markets when using big data.
