Deep Learning-Based Hybrid Model with Multi-Head Attention for Multi-Horizon Stock Price Prediction

Rajesh Kumar Ghosh (), Bhupendra Kumar Gupta, Ajit Kumar Nayak and Samit Kumar Ghosh ()
Additional contact information
Rajesh Kumar Ghosh: Department of Computer Science & Engineering, Siksha ‘O’ Anusandhan (Deemed to Be) University, Bhubaneswar 751030, India
Bhupendra Kumar Gupta: Department of Computer Science & Engineering, Siksha ‘O’ Anusandhan (Deemed to Be) University, Bhubaneswar 751030, India
Ajit Kumar Nayak: Department of Computer Science & IT, Siksha ‘O’ Anusandhan (Deemed to Be) University, Bhubaneswar 751030, India
Samit Kumar Ghosh: Department of Biomedical Engineering & Biotechnology, Khalifa University, Abu Dhabi 127788, United Arab Emirates

JRFM, 2025, vol. 18, issue 10, 1-27

Abstract: The prediction of stock prices is challenging due to their volatility, irregular patterns, and complex time-series structure. Reliably forecasting stock market data plays a crucial role in minimizing financial risk and optimizing investment strategies. However, traditional models often struggle to capture temporal dependencies and extract relevant features from noisy inputs, which limits their predictive performance. To improve this, we developed an enhanced recursive feature elimination (RFE) method that blends the importance of impurity-based features from random forest and gradient boosting models with Kendall tau correlation analysis, and we applied SHapley Additive exPlanations (SHAP) analysis to externally validate the reliability of the selected features. This approach leads to more consistent and reliable feature selection for short-term stock prediction over 1-, 3-, and 7-day intervals. The proposed deep learning (DL) architecture integrates a temporal convolutional network (TCN) for long-term pattern recognition, a gated recurrent unit (GRU) for sequence capture, and multi-head attention (MHA) for focusing on critical information, thereby achieving superior predictive performance. We evaluate the proposed approach using daily stock price data from three leading companies—HDFC Bank, Tata Consultancy Services (TCS), and Tesla—and two major stock indices: Nifty 50 and S&P 500. The performance of our model is compared against five benchmark models: temporal convolutional network (TCN), long short-term memory (LSTM), GRU, Bidirectional GRU, and a hybrid TCN–GRU model. Our method consistently shows lower error rates and higher predictive accuracy across all datasets, as measured by four commonly used performance metrics.

Keywords: deep learning; TCN; GRU; multi-horizon stock forecasting; multi-head attention; SHAP; hybrid feature selection (search for similar items in EconPapers)
JEL-codes: C E F2 F3 G (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1911-8074/18/10/551/pdf (application/pdf)
https://www.mdpi.com/1911-8074/18/10/551/ (text/html)

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:gam:jjrfmx:v:18:y:2025:i:10:p:551-:d:1763024

Access Statistics for this article

JRFM is currently edited by Ms. Chelthy Cheng

More articles in JRFM from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().