报告题目：Covariance Matrix Estimation for Positively Correlated Assets
报告人： 刘伟龙 博士（中山大学）
时间：2026年3月27日 14:15
地点：管理学院A北204
报告内容摘要：
The comovement phenomenon in financial markets creates decision scenarios with positively correlated asset returns. This paper addresses covariance matrix estimation under such conditions, motivated by observations of significant positive correlations in factor-sorted portfolio returns. We demonstrate that fine-tuning eigenvectors linked to weak factors within rotation-equivariant frameworks produces well-conditioned covariance matrix estimates. Our Eigenvector Rotation Shrinkage Estimator (ERSE) pairwise rotates eigenvectors while preserving orthogonality, equivalent to performing multiple linear shrinkage on two distinct eigenvalues. Under a high-dimensional asymptotic framework, we further derive a closed-form optimal threshold that compensates the Marchenko-Pastur downward bias. Empirical results on factor-sorted portfolios demonstrate that ERSE outperforms existing rotation-equivariant estimators in reducing out-of-sample portfolio variance, achieving average risk reductions of 10.52% versus linear shrinkage methods and 12.46% versus nonlinear shrinkage methods.
【刘伟龙个人简介】
刘伟龙，中山大学岭南学院博士后，广东工业大学管理学博士，英国Queen′s University Belfast 联合培养博士。研究兴趣包括投资组合、协方差矩阵估计、前沿机器学习及进化算法在金融决策中的应用。主持国家自然科学基金青年项目（C类）与中国博士后科学基金面上项目各一项；作为核心成员参与中国金融期货交易所、广东证监局、广州期货交易所等委托课题多项。以第一或通讯作者在《IEEE Transactions on Evolutionary Computation》（ABS 4星）《Renewable and Sustainable Energy Reviews》（IF 16.3，2篇）《The British Accounting Review》（ABS 3星）《Applied Soft Computing》《系统工程理论与实践》等国内外知名期刊发表论文。多篇工作论文处于《European Journal of Operational Research》（ABS 4星）《IEEE Transactions on Engineering Management》（ABS 3星）《中国管理科学》等期刊的多轮返修阶段。
欢迎有兴趣的教师，全体博士生、硕士生参加。
管理学院人才办公室
