Bayesian-Optimized LSTM Framework for Accurate Stock Price Prediction
Journal of Applied Informatics and Computing · 16.04.2026 · 10 (2) · 1282-1290
DOI: 10.30871/jaic.v10i2.11756 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Applied Informatics and Computing, online erschienen am 16.04.2026. Verfasst von Muhammad Idham Maulana und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
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.
Zitieren
APA
Maulana, M. I., Anam, S., & Bukhori, H. A. (2026). Bayesian-Optimized LSTM Framework for Accurate Stock Price Prediction. Journal of Applied Informatics and Computing, 10(2), 1282-1290. https://doi.org/10.30871/jaic.v10i2.11756
Vancouver
Maulana MI, Anam S, Bukhori HA. Bayesian-Optimized LSTM Framework for Accurate Stock Price Prediction. Journal of Applied Informatics and Computing. 2026;10(2):1282-1290. doi:10.30871/jaic.v10i2.11756
BibTeX
@article{Maulana2026,
author = {Maulana, Muhammad Idham and Anam, Syaiful and Bukhori, Hilmi Aziz},
title = {Bayesian-Optimized LSTM Framework for Accurate Stock Price Prediction},
journal = {Journal of Applied Informatics and Computing},
year = {2026},
volume = {10},
number = {2},
pages = {1282--1290},
doi = {10.30871/jaic.v10i2.11756}
}
EUVIMED