Machine learning and fund characteristics help to select mutual funds with positive alpha - Article Abstract

Sep 17, 2026

Uploaded by Oliver

Machine-learning methods use mutual-fund characteristics to construct tradable long-only portfolios that generate significant out-of-sample annual alphas, net of all costs. The approach reveals nonlinear interactions between fund characteristics and future performance and shows that past performance is a especially strong predictor for more active funds. Results indicate informational frictions and manager-skill effects that reduce misallocation, and suggest investors benefit from active management only with access to sophisticated predictive models.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages22

Reading Time55 min

AccessFree to download

Abstract

Keywords

1. Introduction

Journal of Financial Economics 150 (2023) 103737 Contents lists available at ScienceDirect Journal of Financial Economics journal [homepage:](homepage: www.elsevier.com/locate/jfec)[ www.elsevier.com/locate/jfec](homepage: www.elsevier.com/locate/jfec) | Machine learning and fund characteristics help to select mutual funds with positive alpha ✩
Victor DeMiguel a,∗ , Javier Gil-Bazo b, Francisco J. Nogales c, André A.P. Santos d
a Management Science and Operations, London Business School, United Kingdom
b Department of Economics and Business, Universitat Pompeu Fabra, Barcelona School of Economics, and UPF Barcelona School of Management, Spain c Department of Statistics, Universidad Carlos III de Madrid, Spain
d CUNEF Universidad, Spain | | | | --- | --- | --- | | A R T I C L E I N F O | | A B S T R A C T | | Dataset link: [https://](https://)
[doi.org/10.17632/rpgb99m5zy.3](doi.org/10.17632/rpgb99m5zy.3) | | Machine-learning methods exploit fund characteristics to select tradable long-only portfolios of mutual funds that earn signiﬁcant out-of-sample annual alphas of 2.4% net of all costs. The methods unveil interactions in the relation between fund characteristics and future performance. For instance, past performance is a particularly strong predictor of future performance for more active funds. Machine learning identiﬁes managers whose skill is not suﬃciently oﬀset by diseconomies of scale, consistent with informational frictions preventing investors from identifying the outperforming funds. Our ﬁndings demonstrate that investors can beneﬁt from active management, but only if they have access to sophisticated prediction methods. | | JEL classiﬁcation: G11
G17
G23
Keywords:
Active asset management Mutual-fund performance Mutual-fund misallocation Machine learning
Tradable strategies Nonlinearities and interactions | | | 1. Introduction Mutual-fund research consistently shows that the average active fund earns negative risk-adjusted returns (alpha) after transaction costs, fees, and other expenses (Sharpe, 1966; Jensen, 1968; Gruber, 1996; Ferreira et al., 2013). Moreover, although several studies document the existence of a subset of managers that outperform their benchmarks (Wermers, 2000; Barras et al., 2010; Fama and French, 2010; Kacper- ✩ Nikolai Roussanov was the editor for this article. A previous version of this manuscript was circulated under the title “Can Machine Learning Help to Select Portfolios of Mutual Funds?” We are grateful for detailed and constructive feedback from an anonymous referee and the editor. We are also grateful for comments from Eddie Anderson, Fahiz Baba-Yara, Paul Borochin, Andrea Buraschi, Joao Cocco, Pasquale Della Corte, Francisco Gomes, Jin Guo, Martin Haugh, Juan Imbet, Marcin Kacperczyk, Howard Kung, Narayan Naik, Jean Pauphilet, Anna Pavlova, Markus Pelger, Zhen Qi, Alexandre Rubesam, Stephen Schaefer, Henri Servaes, Raman Uppal, Michael Young, and Paolo Zaﬀaroni, as well as seminar participants at CUNEF, Imperial College Business School, London Business School, Universidad Autónoma de Madrid, Universidad de Zaragoza, University of Bath, University of Bristol and Université Paris Dauphine and conference participants at the 2021 conference of the French Finance Association, 2021 Finance Forum (Spanish Finance Association), 2021 EFMA annual meeting, 2021 conference of the Brazilian Finance Society, 2021 FMA annual meeting, 2021 INFORMS Annual Meeting, 2021 Paris December Finance Meeting, 2022 Funcas (Jornadas de Análisis Financieroy Big Data), 2022 Global Finance Conference, 2022 UF Research Conference on Machine Learning in Finance, 2023 Oxford-Man Institute Machine Learning in Quantitative Finance Conference, and 2023 SoFiE conference. Javier Gil-Bazo acknowledges ﬁnancial support from the Spanish Government, Ministry of Science and Innovation grant PID2020-118541GB-I00, and Spanish Agencia Estatal de Investigación (AEI), through the S

FAQs

What do machine-learning methods target in selecting mutual funds?

They exploit mutual-fund characteristics to build tradable long-only portfolios that can earn significant out-of-sample alphas net of costs.

How do fund characteristics relate to future performance in the study?

The methods uncover nonlinearities and interactions, and they show past performance is a particularly strong predictor for more active funds.

Why might investors still struggle to identify outperforming funds?

The findings are consistent with informational frictions that prevent investors from properly identifying the funds that will outperform.

Sep 17, 2026

Uploaded by Oliver