Selection of portfolios: a comparative analysis of the five factors of FAMA and FRENCH and artificial neural networks
Abstract
This paper aimed to evaluate the performance of an artificial neural network developed with the objective of identifying standards and classifying securities in Brazilian stock market in portfolios, taking into account the assumptions evidenced in Portfolio Theory by Markowitz (1952) that the formation of portfolios reduces the variability and makes it possible to obtain higher risk-adjusted returns. For this, we used firm-level variables, components of the five factors of Fama and French (2015), which were also used for the assembly of portfolios through the use of multiple linear regression with panel data. The comparative results of the regression methods with panel data and artificial neural networks indicated that both methodologies allowed to obtain returns above the market average, however, that the artificial neural network presents greater capacity to avoid securities that are detrimental to the portfolio and allows smoothing losses in times of instability.Downloads
Download data is not yet available.
Published
2018-06-22
How to Cite
Moreira, K. D. S., & Penedo, A. S. T. (2018). Selection of portfolios: a comparative analysis of the five factors of FAMA and FRENCH and artificial neural networks. Enfoque: Reflexão Contábil, 37(2), 141-155. https://doi.org/10.4025/enfoque.v37i2.38329
Issue
Section
Original Articles
DECLARATION OF ORIGINALITY AND COPYRIGHTS
I Declare that current article is original and has not been submitted for publication, in part or in whole, to any other national or international journal.
The copyrights belong exclusively to the authors. Published content is licensed under Creative Commons Attribution 3.0 (CC BY 3.0) guidelines, which allows sharing (copy and distribution of the material in any medium or format) and adaptation (remix, transform, and build upon the material) for any purpose, even commercially, under the terms of attribution.
Read this link for further information on how to use CC BY 3.0 properly.





