DeMiguel, VictorGil-Bazo, JavierNogales, Francisco J.Santos, André A. P.Universitat Pompeu Fabra. Departament d'Economia i Empresa2024-11-142024-11-142021-03-22http://hdl.handle.net/10230/68568Identifying 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.application/pdfengL'accés als continguts d'aquest document queda condicionat a l'acceptació de les condicions d'ús establertes per la següent llicència Creative CommonsCan machine learning help to select portfolios of mutual funds?<resourceType xmlns="http://datacite.org/schema/kernel-3" resourceTypeGeneral="Other">info:eu-repo/semantics/workingPaper</resourceType><subject xmlns="http://datacite.org/schema/kernel-3" subjectScheme="keyword">mutual fund performance</subject><subject xmlns="http://datacite.org/schema/kernel-3" subjectScheme="keyword">performance predictability</subject><subject xmlns="http://datacite.org/schema/kernel-3" subjectScheme="keyword">active management</subject><subject xmlns="http://datacite.org/schema/kernel-3" subjectScheme="keyword">machine learning</subject><subject xmlns="http://datacite.org/schema/kernel-3" subjectScheme="keyword">elastic net</subject><subject xmlns="http://datacite.org/schema/kernel-3" subjectScheme="keyword">random forests</subject><subject xmlns="http://datacite.org/schema/kernel-3" subjectScheme="keyword">gradient boosting</subject><subject xmlns="http://datacite.org/schema/kernel-3" subjectScheme="keyword">Finance and Accounting</subject><rights xmlns="http://datacite.org/schema/kernel-3">info:eu-repo/semantics/openAccess</rights>