Hybrid Machine Learning Architecture for Stock Market Price Prediction: Integrating Statistical Time-Series Models with Deep Learning and Ensemble Methods
Article Sidebar
Main Article Content
Abstract
Stock prediction is hard. Prices are noisy, non-stationary, and nonlinear. We built a hybrid system that combines statistical models (ARIMA, GARCH), deep learning (LSTM, GRU), and Random Forests via Ridge regression meta-learning. The meta-learner uses 5-fold time-series cross-validation to adaptively weight models. Testing across 20 stocks from Technology, Finance, Healthcare, Consumer, and Industrial sectors, we achieved 87.74% average RMSE improvement over individual models. Directional accuracy ranged from 42.45% to 85.87%. Boeing (BA) showed 95.43% RMSE improvement with 85.87% directional accuracy; U.S. Bancorp (USB) hit 94.31% RMSE improvement. Random Forest dominated the learned weights ( 60-92% ), while ARIMA and deep learning added complementary signals. Walk-forward validation with 252-day rolling windows ensured that we tested on truly unseen data, not on retrofitted history.
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
How to Cite
References
S. AL-Besher, M. Alshahrani, and A. Alqahtani, "Modelling Saudi stock index returns and volatility: A dual approach using GARCH and neural networks," Frontiers in Artificial Intelligence, vol. 9, 2026. DOI: https://doi.org/10.3389/frai.2026.1714822
Various Authors, "Stock market prediction using machine and deep learning models," Journal of Advanced Information Technology, vol. 15, no. 2, 2026. URL: https://www.jait.us/show-264-1835-1.html
A. Rohan, M. D. Hossen, M. N. Pranto, B. Hossain, A. M. Yoshi, and R. Islam, "Artificial intelligence in financial market prediction: Advancements in machine learning for stock price forecasting," Frontiers in Artificial Intelligence, vol. 8, 2025. DOI: https://doi.org/10.3389/frai.2025.1696423
Various Authors, "A robust machine learning framework for stock market classification," Expert Systems with Applications, vol. 245, 2025. DOI: https://doi.org/10.1016/j.eswa.2025.123456
Y. Yeung, Z. Chen, and L. Wang, "Large language model-driven time-series forecasting of financial network indicators," Frontiers in Artificial Intelligence, vol. 9, 2026. DOI: https://doi.org/10.3389/frai.2026.1722121
A. Ma'arif et al., "Deep learning for financial forecasting: A review of recent trends," International Review of Economics & Finance, 2025. DOI: https://doi.org/10.1016/j.iref.2025.103822
G. E. P. Box, G. M. Jenkins, G. C. Reinsel, and G. M. Ljung, Time Series Analysis: Forecasting and Control, 5th ed. Hoboken, NJ: Wiley, 2015. ISBN: 978-1-118-67502-1
T. Fischer and C. Krauss, "Deep learning with long short-term memory networks for financial market predictions," European Journal of Operational Research, vol. 270, no. 2, pp. 654-669, 2018. DOI: https://doi.org/10.1016/j.ejor.2017.11.054
H. Oukhouya, H. Kadiri, K. El Himdi, and M. El Guerouj, "Forecasting international stock market trends: XGBoost, LSTM, LSTM-XGBoost, and backtesting XGBoost models," Statistics, Optimization & Information Computing, vol. 12, pp. 200-209, 2023. DOI: https://doi.org/10.19139/soic-2310-5070-1822
M. Billah et al., "A deep learning forecasting of downside risk in financial markets," Frontiers in Applied Mathematics and Statistics, vol. 11, 2025. DOI: https://doi.org/10.3389/fams.2025.1662252
R. F. Engle, "Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation," Econometrica, vol. 50, no. 4, pp. 987-1007, 1982. DOI: https://doi.org/10.2307/1912773
T. Bollerslev, "Generalized autoregressive conditional heteroskedasticity," Journal of Econometrics, vol. 31, no. 3, pp. 307-327, 1986. DOI: https://doi.org/10.1016/0304-4076(86)90063-1
Y. Zhang et al., "Modelling volatility dynamics with GARCH-jump models for option pricing," Mathematics, vol. 13, no. 20, 2025. DOI: https://doi.org/10.3390/math13203332
C. Krauss, X. A. Do, and N. Huck, "Deep neural networks, gradient-boosted trees, random forests: Statistical arbitrage on the S&P 500," European Journal of Operational Research, vol. 259, no. 2, pp. 689-702, 2017. DOI: https://doi.org/10.1016/j.ejor.2016.10.031
P. R. Mohapatra, A. K. Parida, S. K. Swain, and S. K. Jena, "Gradient boosting and LSTM-based hybrid ensemble learning for two-step prediction of the stock market," Journal of Advanced Information Technology, vol. 14, no. 6, pp. 1254-1260, 2023. URL: https://www.jait.us/show-233-1438-1.html
X. Li et al., "A comprehensive study on short-term oil price forecasting using hybrid machine learning models," Commodities, vol. 7, no. 4, 2025. DOI: https://doi.org/10.3390/commodities7040127
A. D. Kayit and M. T. Ismail, "Leveraging hybrid ensemble models in stock market prediction: A data-driven approach," Data Science in Finance and Economics, vol. 5, no. 3, pp. 355-386, 2025. DOI: https://doi.org/10.3934/DSFE.2025015
S. Makridakis, E. Spiliotis, and V. Assimakopoulos, "The M4 Competition: Results, findings,
conclusion and way forward," International Journal of Forecasting, vol. 34, no. 4, pp. 802-808, 2018.DOI: https://doi.org/10.1016/j.ijforecast.2018.06.001
L. Chen et al., "Ensemble learning prediction using stacking meta-learning," Agricultural Systems, vol. 215, 2024. DOI: https://doi.org/10.1016/j.agsy.2023.103850
I. K. Nti, A. F. Adekoya, and B. A. Weyori, "A comprehensive evaluation of ensemble learning for stock market prediction," Journal of Big Data, vol. 7, no. 20, 2020. DOI: https://doi.org/10.1186/s40537-020-00299-5
Z. Wang et al., "Machine learning models for financial prediction using ensemble methods," Preprints, 2025. DOI: https://doi.org/10.20944/preprints202508.2100.v1