Bayesian-Optimized LSTM Framework for Accurate Stock Price Prediction
DOI:
https://doi.org/10.30871/jaic.v10i2.11756Keywords:
Bayesian optimization, deep learning, financial forecasting, LSTM, stock price predictionAbstract
Stock price prediction remains a challenging task due to the highly volatile and non-linear nature of financial market data. Long Short-Term Memory (LSTM) networks have shown remarkable success in modelling temporal dependencies, yet their predictive performance heavily depends on optimal hyperparameter tuning. Conventional methods such as Grid Search and Random Search are often computationally expensive and suboptimal. This study proposes a systematic and data-driven framework that integrates Bayesian Optimization (BO) to enhance the performance of LSTM models for stock price prediction (LSTM+BO Model). Using Amazon (AMZN) daily stock data from 2019 to 2025, the LSTM+BO model was rigorously compared with a standard LSTM and several deep learning and machine learning benchmarks. All models were evaluated over 25 independent runs to ensure statistical reliability. The results demonstrate that the LSTM+BO model achieved the lowest Mean Absolute Percentage Error (2.4413%) and the highest R² score (0.8736), outperforming all benchmarks. Moreover, the optimized model exhibited greater stability and computational efficiency compared to the default configuration. These findings confirm that BO offers an effective and robust approach for systematically developing accurate and efficient forecasting models in financial analytics, providing a strong foundation for the development of automated and adaptive financial forecasting systems.
Downloads
References
[1] A. Sarkar and G. Vadivu, “An Advanced Ensemble Deep Learning Framework for Stock Price Prediction Using VAE, Transformer, and LSTM Model,” 2025.
[2] Z. Hu, Y. Zhao, and M. Khushi, “A survey of forex and stock price prediction using deep learning,” Applied System Innovation, vol. 4, no. 1, pp. 1–30, 2021, doi: 10.3390/ASI4010009.
[3] T. Fischer and C. Krauss, “Deep learning with long short-term memory networks for financial market predictions,” Eur. J. Oper. Res., vol. 270, no. 2, pp. 654–669, 2018, doi: 10.1016/j.ejor.2017.11.054.
[4] S. Deviana, Nusyirwan, D. Azis, and P. Ferdias, “Analisis Model Autoregressive Integrated Moving Average Data Deret Waktu Dengan Metode Momen Sebagai Estimasi Parameter,” Jurnal Siger Matematika, vol. 02, no. 02, pp. 57–67, 2021.
[5] A. Gifty and Dr. Yang Li, “A Comparative Analysis of LSTM, ARIMA, XGBoost Algorithms in Predicting Stock Price Direction,” Engineering and Technology Journal, vol. 09, no. 08, pp. 4978–4986, 2024, doi: 10.47191/etj/v9i08.50.
[6] S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Comput., vol. 9, no. 8, pp. 1735–1780, 1997, doi: 10.1162/neco.1997.9.8.1735.
[7] Z. Zhang, Comparison of LSTM and ARIMA in Price Forecasting: Evidence from Five Indexes, no. Esfct 2023. Atlantis Press International BV, 2024. doi: 10.2991/978-94-6463-268-2_6.
[8] B. Gautam, S. Kandel, M. Shrestha, and S. Thakur, “Comparative Analysis of Machine Learning Models for Stock Price Prediction: Leveraging LSTM for Real-Time Forecasting,” Journal of Computer and Communications, vol. 12, no. 08, pp. 52–80, 2024, doi: 10.4236/jcc.2024.128004.
[9] S. Mehtab and J. Sen, “Stock Price Prediction Using CNN and LSTM-Based Deep Learning Models,” 2020 International Conference on Decision Aid Sciences and Application, DASA 2020, pp. 447–453, 2020, doi: 10.1109/DASA51403.2020.9317207.
[10] S. Mehtab, J. Sen, and A. Dutta, “Stock Price Prediction Using Machine Learning and LSTM-Based Deep Learning Models | Papers With Code”.
[11] A. Flavia and C. Mio, “Performance Comparison of Standard LSTM and LSTM with Random Search Optimization for Spark New Zealand Limited Stock Price Prediction,” International Journal Artificial Intelligent and Informatics, vol. 3, no. 2, pp. 60–66, 2025, doi: 10.33292/ijarlit.v3i2.48.
[12] A. Parkin, M. Herrera, and D. A. Coley, “Energy or carbon? Exploring the relative size of universal zero carbon and zero energy design spaces,” Building Services Engineering Research and Technology, vol. 40, no. 3, pp. 319–339, May 2019, doi: 10.1177/0143624418815780.
[13] T. Yu and H. Zhu, “Hyper-Parameter Optimization: A Review of Algorithms and Applications,” pp. 1–56, 2020.
[14] P. I. Frazier, “A Tutorial on Bayesian Optimization,” no. Section 5, pp. 1–22, 2018.
[15] B. Dinda, “Gated recurrent neural network with TPE Bayesian optimization for enhancing stock index prediction accuracy,” 2022.
[16] B. K. Chan, O. V. Johnson, X. Chew, K. W. Khaw, M. H. Lee, and A. Alnoor, “Proposed Bayesian Optimization Based LSTM-CNN Model for Stock Trend Prediction,” Computing and Informatics, vol. 43, no. 1, pp. 38–63, 2024, doi: 10.31577/cai_2024_1_38.
[17] W. Huang, Y. Nakamori, and S. Wang, “Stock prediction based on Bayesian-LSTM,” in International Conference on Machine Learning and Cybernetics, 2018. doi: 10.1109/ICMLC.2018.8527025.
[18] B. K. Chan, O. V Johnson, X. Chew, K. W. Khaw, M. H. Lee, and A. Alnoor, “Proposed Bayesian Optimization Based LSTM-CNN Model for Stock Trend Prediction,” Computing and Informatics, vol. 43, no. 1, pp. 38–63, 2024, doi: 10.31577/cai_2024_1_38.
[19] K. Chen, Y. Zhao, and F. Dai, “A Critical Review of Recurrent Neural Networks for Sequence Learning,” in 2015 IEEE International Conference on Big Data (Big Data), Oct. 2015. [Online]. Available: http://arxiv.org/abs/1506.00019
[20] T. Yu and H. Zhu, “Hyper-parameter optimization: A review of algorithms and applications,” arXiv preprint arXiv:2003.05689, 2020.
[21] T. Fischer and C. Krauß, “Deep Learning With Long Short-Term Memory Networks for Financial Market Predictions,” Eur. J. Oper. Res., 2018, doi: 10.1016/j.ejor.2017.11.054.
[22] A. Moghar and M. Hamiche, “Stock market prediction using LSTM recurrent neural network,” Procedia Comput. Sci., vol. 170, pp. 1168–1173, 2020, doi: 10.1016/j.procs.2020.03.049.
[23] P. I. Frazier, “A Tutorial on Bayesian Optimization,” 2018. [Online]. Available: https://arxiv.org/abs/1807.02811
[24] M. Martínez-Ramón, M. Ajith, and A. Rajendra Kurup, Deep Learning: A Practical Introduction., 1st ed. Chichester.
[25] R. Garnett, Bayesian Optimization. Cambridge, UK: Cambridge University Press, 2023. doi: 10.1017/9781108348973.
[26] S. Anam, H. A. Bukhori, A. Maulana, M. I. Maulana, and H. Rasikhun, “An Enhanced Particle Swarm Optimization with Mutation for Mean-Value-at-Risk Portfolio Optimization in the Indonesian Banking Sector,” Jurnal Teknik Informatika (Jutif), vol. 6, no. 4, pp. 2648–2666, 2025, doi: 10.52436/1.jutif.2025.6.4.5191.
[27] D. Chicco, M. J. Warrens, and G. Jurman, “The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation,” PeerJ Comput. Sci., vol. 7, pp. 1–24, 2021, doi: 10.7717/PEERJ-CS.623.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Muhammad Idham Maulana, Syaiful Anam, Hilmi Aziz Bukhori
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
