Search

A Study on Machine Learning-Enhanced Efficient Frontiers in Multifactor Models

Author(s)

Zhongting Wang

Affiliation(s)

School of Economics and Management, Harbin University of Science and Technology, Harbin, Heilongjiang, China

Abstract

Traditional multi-factor models and Markowitz’s efficient frontier theory struggle to adapt to complex financial markets, making machine learning a crucial tool for expanding the efficient frontier of investment portfolios. This paper systematically reviews the research landscape in this field, delineates its developmental stages, and summarizes the current applications and pros and cons of various machine learning algorithms across four dimensions: factor discovery, risk measurement, portfolio optimization, and constraint refinement. The study finds that the current field suffers from issues such as a lack of underlying theory, a fragmented research framework, the presence of pseudo-factors, and overfitting. Based on these findings, future research directions are projected, and it is proposed that the theoretical framework should be strengthened, causal and robust techniques should be integrated, and localized research should be conducted, with the aim of providing guidance for both theoretical exploration and practical applications in this field.

Keywords

Multifactor Models; Efficient Frontier; Machine Learning

References

[1] Markowitz H. Portfolio Selection [J]. The Journal of Finance, 1952, 7 (1):77-91. [2] Fama E F, French K R. Common Risk Factors in the Returns on Stocks and Bonds [J]. Journal of Financial Economics, 1993, 33 (1):3-56. [3] Gu S, Kelly B, Xiu D. Empirical Asset Pricing via Machine Learning [J]. The Review of Financial Studies, 2020, 33 (5):2223-2273. [4] Tan J. Improving portfolio efficiency with principal component analysis [J]. Journal of Portfolio Management, 2012, 38 (3): 87-96. [5] López de Prado M, Simonian J, Fabozzi F J. Enhancing Markowitz’s portfolio selection paradigm with machine learning [J]. Annals of Operations Research, 2024, 346 (1):319-340. [6] Zhao Zhenquan, Ding Zhiguo. Research Progress and Review of Multi-Factor Asset Pricing Models [J]. Economic Perspectives, 2019 (08): 116-132. [7] Zhang Chengsi, Li Jintao. Advances and Challenges in the Application of Machine Learning in Quantitative Factor Investing [J]. China Finance Review International, 2023 (2):89-106. [8] Wang Haoyu. A Study on the Application of Causal Inference in Financial Factor Screening [J]. Statistics & Decision, 2024 (8):172-176. [9] Chen Xingyu. Application of Deep Learning in Multi-Factor Stock Selection for A-Shares and Research on Overfitting Prevention [J]. FinTech Era, 2024 (05): 45-52. [10] Liu Chang. Dynamic Factor Models and Portfolio Efficient Frontier Optimization [J]. Journal of Applied Statistics and Management, 2022 (3): 521-533. [11] Zhou Mingyuan. A Review of the Application of Explainable Machine Learning in Factor Investing [J]. Times Finance, 2024 (12): 68-72. [12] Li Yang, Chen Shoudong. A Review of Methods for Optimizing the Portfolio Efficient Frontier [J]. Contemporary Economic Research, 2021 (05): 91-98.