Enhanced Forecasting of Equity Fund Returns Using Machine Learning (2025)
- Authors:
- USP affiliated authors: BARGOS, FABIANO FERNANDES - EEL ; ROMÃO, ESTANER CLARO - EEL
- Unidade: EEL
- DOI: 10.3390/mca30010009
- Subjects: APRENDIZADO COMPUTACIONAL; MEDIDAS ESTATÍSTICAS
- Keywords: predictive analytics; multi-class classification; model accuracy; quantitative trading; light gradient boosting machine; random forest; extra trees
- Language: Inglês
- Abstract: This paper aims to explore the integration of machine learning with risk and return performance measures, to provide a data-driven approach to identifying opportunities in equity funds. We built a dataset with 72 performance measures in the columns calculated for multiple periods ranging from 1 to 120 months. By shifting the values in the 1- and 3-month return columns, we created two new columns, aligning the data for the month t with the return for the month t + 1. We categorized each row into one of three classes based on the mean and standard deviation of the shifted 1- and 3-month returns during the period. Based on cross-validated accuracy, we focused on the top three classifiers. As a result, the developed models achieved accuracy, recall, and precision values exceeding 0.92 on the test data. In addition, models trained on 1 year of data maintained predictive reliability for up to 2 months into the future, achieving precision above 90% in forecasting funds with 3-month returns above the average. Thus, this study highlights the effectiveness of machine learning in financial forecasting, particularly within the environment of the Brazilian equity market.
- Imprenta:
- Source:
- Título: Mathematical And Computational Applications
- ISSN: 2297-8747
- Volume/Número/Paginação/Ano: v.30, n.1, p.1-15, 2025
- Status:
- Artigo publicado em periódico de acesso aberto (Gold Open Access)
- Versão do Documento:
- Versão publicada (Published version)
- Acessar versão aberta:
-
ABNT
BARGOS, Fabiano Fernandes e ROMAO, Estaner Claro. Enhanced Forecasting of Equity Fund Returns Using Machine Learning. Mathematical And Computational Applications, v. 30, n. 1, p. 1-15, 2025Tradução . . Disponível em: https://doi.org/10.3390/mca30010009. Acesso em: 09 abr. 2026. -
APA
Bargos, F. F., & Romao, E. C. (2025). Enhanced Forecasting of Equity Fund Returns Using Machine Learning. Mathematical And Computational Applications, 30( 1), 1-15. doi:10.3390/mca30010009 -
NLM
Bargos FF, Romao EC. Enhanced Forecasting of Equity Fund Returns Using Machine Learning [Internet]. Mathematical And Computational Applications. 2025 ;30( 1): 1-15.[citado 2026 abr. 09 ] Available from: https://doi.org/10.3390/mca30010009 -
Vancouver
Bargos FF, Romao EC. Enhanced Forecasting of Equity Fund Returns Using Machine Learning [Internet]. Mathematical And Computational Applications. 2025 ;30( 1): 1-15.[citado 2026 abr. 09 ] Available from: https://doi.org/10.3390/mca30010009 - Predicting the Equilibrium Product Formation in Oxy-fuel Combustion of Octane (C8H18) using Numerical Modeling
- Integração de matemática e física por meio da Aprendizagem Baseada em Projetos (ABP): o projeto 'Minha casa, minha energia'
- Desenvolvimento de jogos para apoio no ensino de termologia e termodinâmica no ensino fundamental
- O ensino de programação de computadores em cursos de engenharia no brasil
- A partitioned coupling framework for peridynamics and classical theory: Analysis and simulations.
- A concurrent multiscale coupling framework for peridynamics and classical theory.
- Planejamento e Gestão da Educação Ambiental: Proposta de Plano de Ações e Práticas Ambientais para a Rede Municipal de Ensino Fundamental I do Município de Lorena (SP)
- The Importance of Accurate Boundary Condition in Obtaining Reliable Shearing Stresses on a Torsional Finite Element Simulation
- Assessing the Impact of Changes on Design and Material of Howe Bridgesby Finite Element Analysis
- Managing individuals, collectiveness and environment in Decision Making Process for Businesses (an unpretentious approach)
Informações sobre a disponibilidade de versões do artigo em acesso aberto coletadas automaticamente via oaDOI API (Unpaywall).
Por se tratar de integração com serviço externo, podem existir diferentes versões do trabalho (como preprints ou postprints), que podem diferir da versão publicada.
How to cite
A citação é gerada automaticamente e pode não estar totalmente de acordo com as normas
