Fund price prediction and simulated trading based on machine learning
Jingxiong Gao
School of Statistics and Applied Mathematics, Anhui University of Finance and Economics
DOI: https://doi.org/10.59429/bam.v8i1.13619
Keywords: return prediction; anomaly factors; lightGBM; rolling window; machine learning
Abstract
This paper explores fund return prediction and the performance of long-short strategies via machine learning, taking Chinese open-end equity and partial equity hybrid funds as samples. We construct 13 fund characteristic anomaly factors and verify their explanatory power for fund returns using FamaMacBeth regression. Adopting the LightGBM model with empirical hyperparameters and a 12-month rolling window framework, we predict fund returns, sort funds into ten groups by predicted returns, and build a long-short portfolio by going long on the top group and short on the bottom one. Empirical results reveal a significant return gradient effect across the ten groups. The study verifies the feasibility and profitability of the LightGBM-based long-short strategy, and provides targeted investment implications for different types of investors, highlighting the value of fund characteristic anomaly factors in portfolio optimization.
References
[1] Grinblatt, M., S. Titman and R. Wermers, Momentum investment strategies, portfolio performance, and herding: A study of mutual fund behavior. American Economic Review, 1995. 85(5): p. 1088-1105.
[2] Fama, E.F. and K.R. French, Luck versus skill in the cross-section of mutual fund returns. The journal of finance, 2010. 65(5): p. 1915-1947.
[3] Hou, K., C. Xue and L. Zhang, Replicating anomalies. 2017, National Bureau of Economic Research.
[4] Harvey, C.R., Y. Liu and H. Zhu, … and the cross-section of expected returns. The Review of Financial Studies, 2016. 29(1): p. 5-68.
[5] Feng, G., S. Giglio and D. Xiu, Taming the factor zoo: A test of new factors. The Journal of Finance, 2020. 75(3): p. 1327-1370.
[6] DeMiguel, V., et al., Machine learning and fund characteristics help to select mutual funds with positive alpha. Journal of Financial Economics, 2023. 150(3): p. 103737.
[7] Leippold, M., Q. Wang and W. Zhou, Machine learning in the Chinese stock market. Journal of Financial Economics, 2022. 145(2): p. 64-82.
[8] Li, B. and A.G. Rossi, Selecting mutual funds from the stocks they hold: A machine learning approach. Available at SSRN 3737667, 2020.