Achieving superior stock price predictions with hybrid LSTM models and optimization techniques

Document Type : Research Paper

Authors

1 Department of Applied Mathematics, Shahid Bahonar University of Kerman, Kerman, Iran

2 Department of Computer Science, Shahid Bahonar University of Kerman, Kerman, Iran

Abstract

Stock price forecasting remains a significant challenge in volatile financial markets. This study presents a novel hybrid model, the Long Short-Term Memory Variational Mode Decomposition Lemur Optimizer, which improves prediction accuracy and robustness. This model effectively balances exploration and exploitation during optimization by incorporating Lemur Optimizer's unique leaping and dancing behaviors into Long Short-Term Memory networks. Addressing limitations in prior methodologies, such as Long Short-Term Memory Sin-Cosine Algorithm Autoregressive Integrated Moving Average Generalized Auto Regressive Conditional Heteroskedasticity and Long Short-Term Memory Variational Mode Decomposition Rabbit Optimization Algorithm, the proposed approach captures both linear and nonlinear patterns in financial data. The model performed better than existing models when tested against historical stock data across 13 prominent datasets and across different financial instruments. The research provides a robust framework for enhanced stock price predictions that facilitates more informed investment strategies and improved risk management in the field of financial forecasting.

Keywords

Main Subjects

References

[1] Abasi, A. K., Makhadmeh, S. N., Al-Betar, M. A., Alomari, O. A., Awadallah, M. A., Alyasseri, Z. A. A., & Hadjouni, M. (2022). Lemurs optimizer: A new metaheuristic algorithm for global optimization. Applied Sciences, 12(19), 10057.
[2] Alam, K., Bhuiyan, M. H., ul Haque, I., Monir, M. F., & Ahmed, T. (2024). Enhancing Stock Market Prediction: A Robust LSTM-DNN Model Analysis on 26 Real-Life Datasets. IEEE Access.
[3] Ansari, Y., Yasmin, S., Naz, S., Za ar, H., Ali, Z., Moon, J., & Rho, S. (2022). A deep reinforcement learning-based decision support system for automated stock market trading. IEEE Access, 10, 127469-127501.
[4] Azevedo, B. F., Rocha, A. M. A., & Pereira, A. I. (2024). Hybrid approaches to optimization and machine learning methods: a systematic literature review. Machine Learning, 113(7), 4055-4097.
[5] Bollerslev, T. (1986). Generalized autoregressive conditional heteroskedasticity. Journal of Econometrics, 31(3), 307-327.
[6] Box, G. E., Jenkins, G. M., Reinsel, G. C., & Ljung, G. M. (2015). Time series analysis: forecasting and control. John Wiley & Sons.
[7] Chandar, S. K. (2024). Deep learning framework for stock price prediction using long short-term memory. Soft Computing, 1-11.
[8] Corizzo, R., & Rosen, J. (2024). Stock market prediction with time series data and news headlines: a stacking ensemble approach. Journal of Intelligent Information Systems, 62(1), 27-56.
[9] Dragomiretskiy, K., & Zosso, D. (2014). Variational mode decomposition. IEEE Transactions on Signal Processing, 62(3), 531-544.
[10] Eberhart, R., & Kennedy, J. (1995). A new optimizer using particle swarm theory. In Proceedings of the Sixth International Symposium on Micro Machine and Human Science (pp. 39-43). IEEE.
[11] Fan, C., & Zhang, X. (2024). Stock price nowcasting and forecasting with deep learning. Journal of Intelligent Information Systems, 1-18.
[12] Gil, G. L., Duhamel-Sebline, P., & McCarren, A. (2024). An Evaluation of Deep Learning Models for Stock Market Trend Prediction. arXiv preprint arXiv:2408.12408.
[13] Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735-1780.
[14] Investopedia. (n.d.). Autoregressive Integrated Moving Average (ARIMA). https://www.investopedia.com/terms/a/autoregressive-integrated-moving-average-arima.asp
[15] Kabir, M. R., Bhadra, D., Ridoy, M., & Milanova, M. (2025). LSTM{Transformer-Based Robust Hybrid Deep Learning Model for Financial Time Series Forecasting. Sci, 7(1), 7.
[16] Khashei, M., Bijari, M., & Ardali, G. A. R. (2009). Improvement of auto-regressive integrated moving average models using fuzzy logic and arti cial neural networks (ANNs). Neurocomputing, 72(4-6), 956-967.
[17] Md, A. Q., Kapoor, S., AV, C. J., Sivaraman, A. K., Tee, K. F., Sabireen, H., & Janakiraman, N. (2023).Novel optimization approach for stock price forecasting using multi-layered sequential LSTM. Applied Soft Computing, 134, 109830.
[18] Mirjalili, S. (2016). SCA: A sine cosine algorithm for solving optimization problems. Knowledge-Based Systems, 96, 120-133.
[19] Nau, R.(n.d.). ARIMA forecasting. Duke University. https://people.duke.edu/ rnau/411arim.htm
[20] Olah, C. (2015). Understanding LSTM networks.
[21] Ozupek, O., Yilmaz, R., Ghasemkhani, B., Birant, D., & Kut, R. A. (2024). A Novel Hybrid Model (EMD-TI-LSTM) for Enhanced Financial Forecasting with Machine Learning. Mathematics, 12(17), 2794.
[22] Prata, M., Masi, G., Berti, L., Arrigoni, V., Coletta, A., Cannistraci, I., & Bartolini, N. (2024). Lob-based deep learning models for stock price trend prediction: a benchmark study. Arti cial Intelligence Review, 57(5), 1-45.
[23] Sen, J., Mehtab, S., & Dutta, A. (2021). Stock price prediction using machine learning and LSTM-based deep learning models. Authorea Preprints.
[24] Tayarani-N, M. H. (2018). The Rabbit Optimization Algorithm (ARO). Journal of Computational Science, 25, 22-37.
[25] Xing, Z., He, Y., Wang, X., Shao, K., & Duan, J. (2022). VMD-IARIMA-Based Time-Series Forecasting Model and its Application in Dissolved Gas Analysis. IEEE Transactions on Dielectrics and Electrical Insulation, 30(2), 802-811.
[26] Zhou, Y., & Yan, J. (2020, July). A Hybrid Deep Learning Approach for Systemic Financial Risk Prediction. In International Conference on Computational Science and Its Applications (pp. 859-874). Cham: Springer International Publishing.
[27] Zhang, Y. J., Zhang, H., & Gupta, R. (2023). A new hybrid method with data-characteristic-driven analysis for arti cial intelligence and robotics index return forecasting. Financial Innovation, 9(1), 75.
Journal of Mahani Mathematical Research
Volume 15, Issue 1 - Serial Number 33
January 2026
Pages 373-430

Files

History

  • Receive Date: 25 December 2024
  • Revise Date: 08 June 2025
  • Accept Date: 22 September 2025

Share

How to cite

Statistics