Professor Su Shuhua from the School of Mathematics, Physics and Statistics has guided her postgraduate students to achieve the latest results in the field of artificial intelligence
School of Mathematics, Physics and Statistics; Jing Zhou
Recently, Prof. Su Shuhuaguided Tu Jing, a graduate student of the class of 2024, to publish in “Expert Systems With Applications”, a TOP journal in the field of artificial intelligence and computer science (a Top journal in the first zone of SCI journals of the Chinese Academy of Sciences with an impact factor of 7.5) entitled “A multi-objective mean-variance portfolio selection model combining sequential three-way decision and. regret theory”.
The paper presents a multi-objective mean-variance optimization model that combines sequential three-way decision-making with regret theory in response to the complexity of portfolio selection in financial markets and the non-fully rational behavior of investors. By optimizing asset clustering methods, designing dynamic threshold calculation strategies, and introducing constraints of investor regret, the paper significantly enhances the scientific nature of asset allocation and risk control capabilities, and constructs an experimental platform covering multi-industry data of the Chinese stock market to verify the effectiveness of the model. The experimental results showed that the new model performed better in Sharpe ratio and volatility compared with the traditional cluster-based mean variance model, and demonstrated stronger robustness in extreme market conditions. This provides a new tool for financial investment decisions that takes into account both rational analysis and behavioral psychology, and has efficient practical value in areas such as robo-advisory and asset allocation optimization.
