CFP last date
28 April 2025
Reseach Article

Enhancing Financial Time Series Predictions with a Hybrid BNN-LSTM Approach

by Anika Tahsin Biva, A.B.M. Shahadat Hossain, Md. Shafiul Alom Khan, Iqbal Habib
International Journal of Applied Information Systems
Foundation of Computer Science (FCS), NY, USA
Volume 12 - Number 47
Year of Publication: 2025
Authors: Anika Tahsin Biva, A.B.M. Shahadat Hossain, Md. Shafiul Alom Khan, Iqbal Habib
10.5120/ijais2025452015

Anika Tahsin Biva, A.B.M. Shahadat Hossain, Md. Shafiul Alom Khan, Iqbal Habib . Enhancing Financial Time Series Predictions with a Hybrid BNN-LSTM Approach. International Journal of Applied Information Systems. 12, 47 ( Mar 2025), 1-7. DOI=10.5120/ijais2025452015

@article{ 10.5120/ijais2025452015,
author = { Anika Tahsin Biva, A.B.M. Shahadat Hossain, Md. Shafiul Alom Khan, Iqbal Habib },
title = { Enhancing Financial Time Series Predictions with a Hybrid BNN-LSTM Approach },
journal = { International Journal of Applied Information Systems },
issue_date = { Mar 2025 },
volume = { 12 },
number = { 47 },
month = { Mar },
year = { 2025 },
issn = { 2249-0868 },
pages = { 1-7 },
numpages = {9},
url = { https://www.ijais.org/archives/volume12/number47/enhancing-financial-time-series-predictions-with-a-hybrid-bnn-lstm-approach/ },
doi = { 10.5120/ijais2025452015 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2025-03-26T21:02:55+05:30
%A Anika Tahsin Biva
%A A.B.M. Shahadat Hossain
%A Md. Shafiul Alom Khan
%A Iqbal Habib
%T Enhancing Financial Time Series Predictions with a Hybrid BNN-LSTM Approach
%J International Journal of Applied Information Systems
%@ 2249-0868
%V 12
%N 47
%P 1-7
%D 2025
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Accurate forecasting of stock market indices is vital for guiding investment strategies and mitigating financial risks. This study proposes a novel hybrid Bayesian Neural Network-Long Short- Term Memory (BNN-LSTM) model to enhance the predictive accuracy of Dow Jones Industrial Average (DJIA) closing price forecasts. By integrating the uncertainty quantification capabilities of Bayesian Neural Networks with the sequential learning strengths of Long Short-Term Memory networks, the hybrid model addresses the challenges of modeling complex, nonlinear, and timedependent financial data. Comparative experiments were conducted using Bayesian Neural Networks, LSTM, Random Forest (RF), Gradient Boosting Machine (GBM), and the hybrid BNN-LSTM model on historical DJIA data spanning January 1, 2005, to December 31, 2022, for training, and January 1, 2023, to January 31, 2024, for testing. The hybrid BNN-LSTM consistently outperformed all competing models across multiple evaluation metrics. These results underscore the model’s superior ability to capture complex market dynamics and its robustness in forecasting financial time series. This study contributes a powerful tool for financial decision-making and sets the foundation for future advancements in hybrid deep learning models for stock market analysis.

References
  1. Ticknor, J. L. (2013). A Bayesian regularized artificial neural network for stock market forecasting. Expert Systems With Applications, 40(14), 5501–5506. https: // doi. org/ 10. 1016/ j. eswa. 2013. 04. 013
  2. Selvamuthu, D., Kumar, V., & Mishra, A. (2019). Indian stock market prediction using artificial neural networks on tick data. Financial Innovation, 5(1). https: // doi. org/ 10. 1186/ s40854-019-0131-7
  3. Althelaya, K. A., El-Alfy, E.-S. M., & Mohammed, S. (2018). Evaluation of bidirectional LSTM for short-and long-term stock market prediction. 2018 9th International Conference on Information and Communication Systems (ICICS), Irbid, Jordan, 151-156. https: // doi. org/ 10. 1109/ IACS. 2018. 8355458
  4. Yan, D., Zhou, Q., Wang, J., & Zhang, N. (2016). Bayesian regularisation neural network based on artificial intelligence optimisation. International Journal of Production Research, 55(8), 2266–2287. https: // doi. org/ 10. 1080/ 00207543. 2016. 1237785
  5. Park, H. J., Kim, Y., & Kim, H. Y. (2021). Stock market forecasting using a multi-task approach integrating long shortterm memory and the random forest framework. Applied Soft Computing, 114, 108106. https: // doi. org/ 10. 1016/ j. asoc. 2021. 108106
  6. Vazirani, S., Sharma, A., & Sharma, P. (2020). Analysis of various machine learning algorithm and hybrid model for stock market prediction using python. 2020 International Conference on Smart Technologies in Computing, Electrical and Electronics (ICSTCEE), Bengaluru, India, 203–207. https: // doi. org/ 10. 1109/ ICSTCEE49637. 2020. 9276859
  7. Bola, A. A., Adesola, A. G., Omidiora, E. O., & Adebisi, A. A. (2013). Forecasting movement of the Nigerian stock exchange all share index using artificial neural and Bayesian networks. Journal of Finance and Investment Analysis, 2(1).
  8. Omar, A. B., Huang, S., Salameh, A. A., Khurram, H., & Fareed, M. (2022). Stock market forecasting using the random forest and deep neural network models before and during the COVID-19 period. Frontiers in Environmental Science, 10. https: // doi. org/ 10. 3389/ fenvs. 2022. 917047
  9. Garg, S. (2021). Forecasting of Gold Prices Using Bayesian Regularization Neural Network. In Nath, V., & Mandal, J. (Eds.), Nanoelectronics, Circuits and Communication Systems. Lecture Notes in Electrical Engineering, vol. 692, Springer, Singapore. https: // doi. org/ 10. 1007/ 978-981-15-7486-3_ 15
  10. Vullam, N., Yakubreddy, K., Vellela, S. S., Basha Sk, K., R. B., V., & Santhi Priya, S. (2023). Prediction and analysis using a hybrid model for stock market. 2023 3rd International Conference on Intelligent Technologies (CONIT), Hubli, India, 1–5. https: // doi. org/ 10. 1109/ CONIT59222. 2023. 10205638
  11. Hajiaghajani, A. (2023). Designing a combined Markovbayesian model in order to predict stock prices in the stock exchange. International Journal of Innovation in Management Economics and Social Sciences, 3(2), 33–41. https: // doi. org/ 10. 59615/ ijimes. 3. 2. 33
  12. Pandya, A., Kapoor, V., & Joshi, A. (2024). Stock market prediction using ARIMA-LSTM hybrid. Journal of Information and Optimization Sciences, 45(4), 1129–1139. https: // doi. org/ 10. 47974/ jios-1697
  13. Hossain, S., & Kaur, G. (2024). Stock market prediction: XGBoost and LSTM comparative analysis. 2024 3rd International Conference on Artificial Intelligence for Internet of Things (AIIoT), Vellore, India, 1–6. https: // doi. org/ 10. 1109/ AIIoT58432. 2024. 10574794
  14. Adeleye, N. R. A., Tubokirifuruar, N. T. S., Bello, N. B. G., Ndubuisi, N. N. L., Asuzu, N. O. F., & Owolabi, N. O. R. (2024). Machine learning for stock market forecasting: A review of models and accuracy. Finance & Accounting Research Journal, 6(2), 112–124. https: // doi. org/ 10. 51594/ farj. v6i2. 783
  15. Wu, M. (2021). Financial transaction forecasting using neural network and Bayesian optimization. 2021 IEEE International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI), Fuzhou, China, 193–196. https: // doi. org/ 10. 1109/ CEI52496. 2021. 9574535
  16. Maeda, I., et al. (2020). Learning uncertainty in market trend forecast using Bayesian neural networks. In Bucciarelli, E., Chen, S. H., & Corchado, J. (Eds.), Decision Economics: Complexity of Decisions and Decisions for Complexity. Advances in Intelligent Systems and Computing, vol. 1009, Springer, Cham. https: // doi. org/ 10. 1007/ 978-3-030-38227-8_ 24
  17. Su, Z., & Zhao, Z. (2022). A Bayesian financial panel data model based on neural network algorithm. 2022 IEEE 2nd International Conference on Mobile Networks and Wireless Communications (ICMNWC), Tumkur, Karnataka, India, 1–5. https: // doi. org/ 10. 1109/ ICMNWC56175. 2022. 10031896
  18. Alam, K., Bhuiyan, M. H., Haque, I. U., Monir, M. F., & Ahmed, T. (2024). Enhancing stock market prediction: A robust LSTM-DNN model analysis on 26 real-life datasets. IEEE Access, 12, 122757–122768. https: // doi. org/ 10. 1109/ ACCESS. 2024. 3434524
  19. Satyaveer, P., Patel, H., Chandra, P., Pal, P., & Singh, S. K. (2023). A new hybrid model ARFIMA-LSTM combined with news sentiment analysis model for stock market prediction. 2023 Third International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT), Bhilai, India, 1–5. https: // doi. org/ 10. 1109/ ICAECT57570. 2023. 10118349
  20. Singh, D., & Singh, B. (2020). Investigating the impact of data normalization on classification performance. Applied Soft Computing, 97, 105524. Elsevier.
  21. Izmailov, P., Vikram, S., Hoffman, M. D., & Wilson, A. G. G. (2021). What are Bayesian neural network posteriors really like? In Proceedings of the International Conference on Machine Learning (pp. 4629–4640). PMLR.
  22. Hern´andez-Lobato, J. M., & Adams, R. (2015). Probabilistic backpropagation for scalable learning of Bayesian neural networks. In Proceedings of the International Conference on Machine Learning (pp. 1861–1869). PMLR.
  23. Biva, A. T., Khan, M. S. A., & Hossain, A. S. (2024). A Comparative Study of ARIMA, Artificial Neural Networks, and Kalman Filter Models for Dhaka Stock Exchange Forecasting. GANIT: Journal of Bangladesh Mathematical Society, 44(1), 29–58.
Index Terms

Computer Science
Information Sciences
Hybrid Model
Closing Price Forecasting

Keywords

Stock market forecasting hybrid BNN-LSTM model neural networks deep learning in finance time series prediction