Machine Learning and Fund Characteristics Help to Select Mutual Funds with Positive Alpha

66 Pages Posted: 16 Mar 2021 Last revised: 19 Sep 2022

See all articles by Victor DeMiguel

Victor DeMiguel

London Business School

Javier Gil-Bazo

Universitat Pompeu Fabra; UPF Barcelona School of Management; Barcelona School of Economics

Francisco J. Nogales

Universidad Carlos III de Madrid - Department of Statistics; Institute of Financial Big Data UC3M-BS

Andre A. P. Santos

University of Edinburgh - Edinburgh Business School; Universidade Federal de Santa Catarina (UFSC) - Department of Economics

Date Written: January 28, 2021

Abstract

Nonlinear machine-learning methods select tradable long-only portfolios of mutual funds that earn significant out-of-sample alphas of 2.3% per year net of all costs. In contrast, linear methods deliver insignificant alphas. Machine learning unveils important interactions between fund activeness and past performance--to earn positive alpha, investors should choose more active funds conditional on their having good past performance, but less active funds conditional on poor past performance. Our findings demonstrate that investors can bene t from active management, but only if they have access to the predictions of sophisticated methods that capture complexity in the relation between fund characteristics and performance.

Keywords: Mutual-fund performance; performance predictability; active management; elastic net; random forests; gradient boosting.

JEL Classification: G23, G11, G17

Suggested Citation

DeMiguel, Victor and Gil-Bazo, Javier and Nogales, Francisco J. and A. P. Santos, Andre, Machine Learning and Fund Characteristics Help to Select Mutual Funds with Positive Alpha (January 28, 2021). Proceedings of Paris December 2021 Finance Meeting EUROFIDAI - ESSEC, Available at SSRN: https://ssrn.com/abstract=3768753 or http://dx.doi.org/10.2139/ssrn.3768753

Victor DeMiguel

London Business School ( email )

Sussex Place
Regent's Park
London, London NW1 4SA
United Kingdom

Javier Gil-Bazo

Universitat Pompeu Fabra ( email )

Ramon Trias Fargas, 25-27
Barcelona, 08005
Spain

UPF Barcelona School of Management ( email )

Carrer de Balmes, 132, 134
Barcelona, 08008
Spain

Barcelona School of Economics ( email )

Ramon Trias Fargas, 25-27
Barcelona, Barcelona 08005
Spain

Francisco J. Nogales

Universidad Carlos III de Madrid - Department of Statistics ( email )

Avda. de la Universidad, 30
Leganes, Madrid 28911
Spain
+34 916248773 (Phone)

HOME PAGE: http://www.est.uc3m.es/Nogales

Institute of Financial Big Data UC3M-BS ( email )

CL. de Madrid 126
Madrid, Madrid 28903
Spain

Andre A. P. Santos (Contact Author)

University of Edinburgh - Edinburgh Business School ( email )

29 Buccleuch Pl
Edinburgh, Scotland EH8 9JS
United Kingdom

Universidade Federal de Santa Catarina (UFSC) - Department of Economics ( email )

PO Box 476
Florianopolis, SC 88010-970
Brazil

HOME PAGE: http://sites.google.com/site/andreportela

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
1,545
Abstract Views
4,606
rank
17,290
PlumX Metrics