Investor Sentiment on the Stock Market using Artificial Neural Networks

Oana Mădălina Popescu
Additional contact information
Oana Mădălina Popescu: The Bucharest University of Economic Studies

REVISTA DE MANAGEMENT COMPARAT INTERNATIONAL/REVIEW OF INTERNATIONAL COMPARATIVE MANAGEMENT, 2019, vol. 20, issue 5, 508-518

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 sentiment; volatility; artificial neural network; GARCH(1,1) model; GARCH-t(1,1) model. (search for similar items in EconPapers)
JEL-codes: C01 C12 C13 G17 G41 (search for similar items in EconPapers)
Date: 2019
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.rmci.ase.ro/no20vol5/01.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:rom:rmcimn:v:20:y:2019:i:5:p:508-518

Access Statistics for this article

REVISTA DE MANAGEMENT COMPARAT INTERNATIONAL/REVIEW OF INTERNATIONAL COMPARATIVE MANAGEMENT is currently edited by Marian Nastase

More articles in REVISTA DE MANAGEMENT COMPARAT INTERNATIONAL/REVIEW OF INTERNATIONAL COMPARATIVE MANAGEMENT from Faculty of Management, Academy of Economic Studies, Bucharest, Romania Contact information at EDIRC.
Bibliographic data for series maintained by Marian Nastase ().