Título An experimental study on diversification in portfolio optimization
Autores Martínez-Nieto L. , FERNÁNDEZ NAVARRO, FRANCISCO DE ASÍS, CARBONERO RUZ, MARIANO, MONTERO ROMERO, Mª TERESA
Publicación externa No
Medio Expert Syst. Appl.
Alcance Article
Naturaleza Científica
Cuartil JCR 1
Cuartil SJR 1
Impacto JCR 8.66500
Impacto SJR 2.07000
Web https://www.scopus.com/inward/record.uri?eid=2-s2.0-85106308418&doi=10.1016%2fj.eswa.2021.115203&partnerID=40&md5=c791aa830769e2467437769cf0c05ca0
Fecha de publicacion 01/01/2021
ISI 000663582700009
Scopus Id 2-s2.0-85106308418
DOI 10.1016/j.eswa.2021.115203
Abstract New diversification strategies, along with other naive strategies as 1/N portfolios, have been proposed in the literature as a method for overcoming concentration limitations of the mean–variance model. However, it is not clear whether these strategies outperform the classical mean–variance model in all scenarios. Motivated by these points, this manuscript contributes an experimental study in which 11 diversification and mean–variance strategies are compiled and compared with a complete repository of 10 portfolio time series problems with three different estimation windows (composing a total of 30 datasets) and then evaluated using four performance metrics. Additionally, a novel purely data-driven method for determining the optimal value of the hyper-parameter associated with each approach is also proposed. Unlike results previously found in the literature, the empirical results obtained in this study show that equally weighed models obtain the worst ranking in all evaluation metrics except for the stability index, which is hypothetically due to the hyper-parameter optimization raising the transaction cost debate. © 2021 Elsevier Ltd
Palabras clave 1/N portfolio; Diversification strategies; Hyper-parameter optimization; Mean–variance portfolio; Out-of-sample performance
Miembros de la Universidad Loyola

Change your preferences Gestionar cookies