Paper #1772

Título:

Can machine learning help to select portfolios of mutual funds?

Autores:

Victor DeMiguel, Javier Gil-Bazo, Francisco J. Nogales y André A. P. Santos

Fecha:

Marzo 2021

Resumen:

Identifying outperforming mutual funds ex-ante is a notoriously difficult task. We use machine learning methods to exploit the predictive ability of a large set of mutual fund characteristics that are readily available to investors. Using data on US equity funds in the 1980-2018 period, the methods allow us to construct portfolios of funds that earn positive and significant out-of-sample risk-adjusted after-fee returns as high as 4.2% per year. We further show that such outstanding performance is the joint outcome of both exploiting the information contained in multiple fund characteristics and allowing for flexibility in the relationship between predictors and fund performance. Our results confirm that even retail investors can benefit from investing in actively managed funds. However, we also find that the performance of all our portfolios has declined over time, consistent with increased competition in the asset market and diseconomies of scale at the industry level.

Palabras clave:

Mutual fund performance, performance predictability, active management, machine learning, elastic net, random forests, gradient boosting

Área de investigación:

Finanzas y Contabilidad

Descargar el paper en formato PDF (858 Kb)