Stock market trend prediction using a sparse Bayesian framework

Author

Markovic, Ivana P. ; Stojanovic, Milos B. ; Bozic, Milos M.

Author_Institution

Fac. of Econ., Univ. of Nis, Niš, Serbia

fYear

2014

fDate

25-27 Nov. 2014

Firstpage

207

Lastpage

210

Abstract

The aim of this study is to develop a relevance vector machine-a RVM classifier for trend prediction of the BELEX15 index of the Belgrade Stock Exchange. In addition, the RVM model is compared to two `similar´ methods: support vector machines - SVMs and least squares support vector machines - LS-SVMs to analyze their classification precisions and complexity. The test results indicate tha tRVMs outperform benchmarking models and are suitable for short-term stock market trend predictions.

Keywords

Bayes methods; least squares approximations; pattern classification; stock markets; support vector machines; BELEX15 index; Belgrade Stock Exchange; LS-SVM; RVM classifier; benchmarking models; classification complexity; classification precisions; least squares support vector machines; relevance vector machine; sparse Bayesian framework; stock market trend prediction; tRVM; Bayes methods; Indexes; Market research; Predictive models; Stock markets; Support vector machines; Training; Classification; relevance vector machines; sparse Bayesian framework; stock market trend prediction;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Network Applications in Electrical Engineering (NEUREL), 2014 12th Symposium on

Conference_Location

Belgrade

Print_ISBN

978-1-4799-5887-0

Type

conf

DOI

10.1109/NEUREL.2014.7011508

Filename

7011508