Hybrid deep learning approach for financial time series classification

Authors

  • Carlos A. S. Assis
  • Eduardo J. Machado
  • Adriano C. M. Pereira
  • Eduardo G. Carrano

DOI:

https://doi.org/10.5335/rbca.v10i2.7904

Keywords:

Restricted Boltzmann Machines, Machine Learning, Stock Market

Abstract

This paper proposes a combined approach of two machine learning techniques for financial time series classification. Boltzmann Restricted Machines (RBM) were used as the latent features extractor and Support Vector Machines (SVM) as the classifier. Tests were performed with real data of five assets from Brazilian Stock Market. The results of the combined RBM + SVM techniques showed better performance when compared to the isolated SVM, which suggests that the proposed approach can be suitable for the considered application.

Downloads

Download data is not yet available.

Downloads

Published

2018-07-17

Issue

Section

Original Paper

How to Cite

[1]
2018. Hybrid deep learning approach for financial time series classification. Brazilian Journal of Applied Computing. 10, 2 (Jul. 2018), 54–63. DOI:https://doi.org/10.5335/rbca.v10i2.7904.