Hybrid deep learning approach for financial time series classification | Zendy

Carlos A. S. Assis | Zendy; Eduardo Jabbur Machado | Zendy; Adriano C. M. Pereira | Zendy; Eduardo G. Carrano | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Hybrid deep learning approach for financial time series classification

Author(s) -

Carlos A. S. Assis,

Eduardo Jabbur Machado,

Adriano C. M. Pereira,

Eduardo G. Carrano

Publication year - 2018

Publication title -

revista brasileira de computação aplicada

Language(s) - English

Resource type - Journals

ISSN - 2176-6649

DOI - 10.5335/rbca.v10i2.7904

Subject(s) - support vector machine , extractor , artificial intelligence , computer science , machine learning , boltzmann machine , time series , stock market , classifier (uml) , series (stratigraphy) , pattern recognition (psychology) , deep learning , data mining , engineering , horse , paleontology , process engineering , biology

This paper proposes a combined approach of two machine learning techniques for nancial time series classi cation. Boltzmann Restricted Machines (RBM) were used as the latent features extractor and Support Vector Machines (SVM) as the classi er. Tests were performed with real data of ve 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.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research