Robustness in Portfolio Optimization
讨论了投资组合优化中稳健性的重要性，介绍了稳健估计量、稳健优化、分布稳健优化和基于场景的优化等方法，并回顾了数据驱动和机器学习模型。
Portfolio optimization is the basic quantitative approach for finding optimal portfolio weights. It has become increasingly important as portfolio construction involves more and more data and automated approaches. The inherent uncertainty in financial markets has led to consistent demand for improved robustness of portfolio models. In this article, the authors discuss the importance of robustness in portfolio optimization and present powerful methods that include robust estimators, robust portfolio optimization, distributionally robust optimization, and scenario-based optimization. They also review data-driven methods, machine learning–based models, and practical approaches for improving portfolio robustness.