Hybrid Machine Learning Architecture for Stock Market Price Prediction: Integrating Statistical Time-Series Models with Deep Learning and Ensemble Methods
International Journal of Emerging Science and Engineering · 30.03.2026 · 14 (4) · 13-22
DOI: 10.35940/ijese.f8335.14040326 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Emerging Science and Engineering, online erschienen am 30.03.2026. Verfasst von Sridhanush Varma und 4 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben.
Abstract (Originalsprache)
Stock prediction is hard. Prices are noisy, nonstationary, 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 percent average RMSE improvement over individual models. Directional accuracy ranged from 42.45 percent to 85.87 percent. Boeing (BA) showed 95.43 percent RMSE improvement with 85.87 percent directional accuracy, U.S. Bancorp (USB) hit 94.31 percent RMSE improvement. Random Forest dominated the learned weights (60-92 percent), 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.
Zitieren
APA
Varma, S., Rao, R. S., Teja, P. R., Shiva, M., & Ramana, D. B. V. (2026). Hybrid Machine Learning Architecture for Stock Market Price Prediction: Integrating Statistical Time-Series Models with Deep Learning and Ensemble Methods. International Journal of Emerging Science and Engineering, 14(4), 13-22. https://doi.org/10.35940/ijese.f8335.14040326
Vancouver
Varma S, Rao RS, Teja PR, Shiva M, Ramana DBV. Hybrid Machine Learning Architecture for Stock Market Price Prediction: Integrating Statistical Time-Series Models with Deep Learning and Ensemble Methods. International Journal of Emerging Science and Engineering. 2026;14(4):13-22. doi:10.35940/ijese.f8335.14040326
BibTeX
@article{Varma2026,
author = {Varma, Sridhanush and Rao, R. Swejan and Teja, P. Ravi and Shiva, M. and Ramana, Dr. B. Venkata},
title = {Hybrid Machine Learning Architecture for Stock Market Price Prediction: Integrating Statistical Time-Series Models with Deep Learning and Ensemble Methods},
journal = {International Journal of Emerging Science and Engineering},
year = {2026},
volume = {14},
number = {4},
pages = {13--22},
doi = {10.35940/ijese.f8335.14040326}
}
EUVIMED