Article  /  Volume 20, Issue 5  /  2019

Investor Sentiment on the Stock Market using Artificial Neural Networks

Oana Mădălina POPESCU

Published
2019
Volume & issue
20 (5)
Pages
508–518
DOI
10.24818/RMCI.2019.5.508

Download PDFHow to cite

Abstract

The present study uses volatility as a measure of investor sentiment on the Romanian capital market. The GARCH(1,1) model and the GARCH(1,1) model with Student-t innovations are used in order to describe the volatility of the Bucharest Exchange Trading index. The estimated volatility series are afterwards included into two artificial neural networks with the purpose to evaluate the forecasting performance of these networks. The results show that even though the artificial neural networks are well specified the volatility of the BET index, as measured by the GARCH(1,1) and GARCH-t(1,1) models, does not represent a proper measure for investor sentiment on the market.

Keywords

investor sentimentvolatilityartificial neural networkGARCH(11) modelGARCH-t(11) model

JEL classification

C01, C12, C13, G17, G41

How to cite

Oana Mădălina POPESCU (2019). Investor Sentiment on the Stock Market using Artificial Neural Networks. Review of International Comparative Management, 20(5), 508–518. DOI: 10.24818/RMCI.2019.5.508