Machine learning the performance of hedge fund

Tian Ma, Wanwan Wang and Fuwei Jiang

Journal of International Money and Finance, 2025, vol. 155, issue C

Abstract: This study utilizes generative AI to predict and classify the performance of hedge funds based on groups of fund characteristics. Compared to commonly used machine learning methods, our method can successfully distinguish high- and low-performing funds across various investment strategies, with the return spread being the highest in the equity hedge strategy at 3.16 % monthly. The results are robust in risk-adjusted return prediction. Trend-based features are the most important predictors of future fund performance. Returns of predictive long-short portfolios are higher following periods of low narrative attention and favorable macroeconomic conditions. The asset allocation exercise highlights the significant economic value of machine learning. Our study enriches the burgeoning field of machine learning and artificial intelligence for finance by applying big data techniques to fund selection and allocation.

Keywords: Hedge Fund Performance; Machine Learning; Fund Characteristic; Big data; Artificial Intelligence for Finance (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0261560625000671
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:jimfin:v:155:y:2025:i:c:s0261560625000671

DOI: 10.1016/j.jimonfin.2025.103332

Access Statistics for this article

Journal of International Money and Finance is currently edited by J. R. Lothian

More articles in Journal of International Money and Finance from Elsevier
Bibliographic data for series maintained by Catherine Liu ().