PREDICTING STOCK PRICE DIRECTION OF EUROZONE BANKS: CAN DEEP LEARNING TECHNIQUES OUTPERFORM TRADITIONAL MODELS?

Bogdan Ionuț Anghel
Additional contact information
Bogdan Ionuț Anghel: Faculty of International Business and Economics, Bucharest University of Economic Studies, Bucharest, Romania.

Studii Financiare (Financial Studies), 2024, vol. 28, issue 4, 29-42

Abstract: Due to market volatility and complex regulations, forecasting stock price movements within the European banking sector is highly challenging. This study compares the predictive performance of Bidirectional Long Short-Term Memory (BiLSTM) and Long Short-Term Memory (LSTM) with traditional models - Extreme Gradient Boosting (XGBoost) and Logistic Regression - in predicting the daily stock price direction of the ten largest Eurozone banks by market capitalization. Utilizing a dataset from January 1, 2000, to May 31, 2024, comprising eight financial and macroeconomic indicators, a comparative analysis of these models was conducted. The findings suggest that traditional machine learning models are more effective than advanced deep learning models for predicting stock price direction in the Eurozone banking sector. The underperformance of LSTM and BiLSTM may be attributed to dataset limitations relative to deep learning requirements.

Keywords: Financial Market; European Banking Sector; Time Series; Prediction (search for similar items in EconPapers)
JEL-codes: C53 G12 G17 G21 (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.icfm.ro/RePEc/vls/vls_pdf/vol28i4p29-42.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:vls:finstu:v:28:y:2024:i:4:p:29-42

Access Statistics for this article

More articles in Studii Financiare (Financial Studies) from Centre of Financial and Monetary Research "Victor Slavescu" Contact information at EDIRC.
Bibliographic data for series maintained by Daniel Mateescu ().