OPTIMIZATION OF LSTM HYPERPARAMETERS USING GREY WOLF OPTIMIZATION AND HYPERBAND FOR PREDICTING BRI STOCK PRICES
Published:
2026-07-27Downloads
Abstract
This research compares the performance of the Hyperband and Grey Wolf Optimization (GWO) algorithms in optimizing the hyperparameters of the Long Short-Term Memory (LSTM) model for predicting the stock price of Bank Rakyat Indonesia (BRI). Stock price prediction is a complex problem due to the dynamic and nonlinear characteristics of time series data. The dataset used consists of historical BRI stock data for the 2018-2025 period, obtained from Yahoo Finance. The optimization process was performed on several LSTM hyperparameters, including units, learning rate, dropout, optimizer, batch size, and epoch. Model performance was evaluated using Root Mean Square Error (RMSE). The results show that the LSTM-GWO model outperforms the LSTM-Hyperband model, with an RMSE of 75.93 compared to 77.60. However, Hyperband is more computationally efficient than GWO. The findings indicate that the GWO algorithm is more effective at improving prediction accuracy, while Hyperband excels in tuning efficiency. This study is expected to contribute to the development of hyperparameter optimization methods for deep learning models used in time-series-based stock price prediction.
Keywords:
LSTM Grey Wolf Optimization Stock Price Prediction Hyperband Hyperparameter OptimizationReferences
Anam, K. (2026, April 28). Bukti BBRI Jadi Saham Rakyat, Jumlah Investor Ritel Capai 700 Ribu. CNBC Indonesia. https://www.cnbcindonesia.com/market/20260428165642-17-730659/bukti-bbri-jadi-saham-rakyat-jumlah-investor-ritel-capai-700-ribu
Andika, R., & Kusrini, K. (2025). Optimasi Hyperparameter Model Lstm Dan Variannya Untuk Peramalan Pembelian Bahan Baku Karet Alam. JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika), 10(3), 2627–2639. https://doi.org/10.29100/jipi.v10i3.7567
Deswal, V. (2024). Hyperparameter Tuning of the LSTM model for Stock Price Prediction. International Journal of Intelligent Systems and Applications in Engineering, 12(4), 705–712.
Dhake, H., Kashyap, Y., & Kosmopoulos, P. (2023). Algorithms for Hyperparameter Tuning of LSTMs for Time Series Forecasting. Remote Sensing, 15(8), 2076. https://doi.org/10.3390/rs15082076
Dilawar, M., & Shahbaz, M. (2025). A Bayesian Optimized Stacked Long Short-Term Memory Framework for Real-Time Predictive Condition Monitoring of Heavy-Duty Industrial Motors. Computers, Materials & Continua, 83(3), 5091–5114. https://doi.org/10.32604/cmc.2025.064090
Djaballah, S., Saidi, L., Meftah, K., Hechifa, A., Bajaj, M., & Zaitsev, I. (2024). A hybrid LSTM random forest model with grey wolf optimization for enhanced detection of multiple bearing faults. Scientific Reports, 14, 23997. https://doi.org/10.1038/s41598-024-75174-x
Duha, A. M., & Putra, A. T. (2025). Optimasi Hyperparameter Pada Model Hybrid Bidirectional LSTM-GRU Untuk Prediksi Harga Saham Bank. Bulletin of Computer Science Research, 6(1), 332–341. https://doi.org/10.47065/bulletincsr.v6i1.903
Eren, B., Erden, C., Atalı, A., & Ozdemir, S. (2025). A comparative analysis of hyperparameter optimization using LSTM-based deep learning models for urban air quality predictions. Ain Shams Engineering Journal, 16(12), 103786. https://doi.org/10.1016/j.asej.2025.103786
Hao, J., Shang, S., Yuan, J., & Li, J. (2024). Do multisource data matter for NGP prediction? Evidence from the G-LSTM model. Heliyon, 10(12), e33387. https://doi.org/10.1016/j.heliyon.2024.e33387
Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
Kazemi, M., Samani, R. N., & Kariminejad, N. (2026). Optimizing LSTM networks and feature selection algorithms using GEE data. PLOS ONE, 21(4), e0347858. https://doi.org/10.1371/journal.pone.0347858
Khayat, A., Kissaoui, M., Bahatti, L., Raihani, A., Errakkas, K., & Atifi, Y. (2025). Efficient day-ahead energy forecasting for microgrids using LSTM optimized by grey wolf algorithm. E-Prime - Advances in Electrical Engineering, Electronics and Energy, 13, 101054. https://doi.org/10.1016/j.prime.2025.101054
Li, L., Jamieson, K., DeSalvo, G., Rostamizadeh, A., & Talwalkar, A. (2018). Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization.
Li, S., Wang, T., Li, G., Skulstad, R., & Zhang, H. (2024). Short-term ship roll motion prediction using the encoder–decoder Bi-LSTM with teacher forcing. Ocean Engineering, 295, 116917. https://doi.org/10.1016/j.oceaneng.2024.116917
Listyaningrum, R., Purwanto, R., Prasetyanti, D. N., Vikasari, C., & Pratiwi, A. F. (2025). Pemanfaatan Algoritma Random Forest Regression dalam Memprediksi Kepuasan Mahasiswa Terhadap Dosen. Infotekmesin, 16(2), 408–416. https://doi.org/10.35970/infotekmesin.v16i2.2808
Mahardhika, F., Yulianti, K., & Kustiawan, C. (2025). Algoritma Grey Wolf Optimizer dan Model Mean Absolute Deviation Untuk Optimisasi Portofolio Saham. Jurnal EurekaMatika, 13(1), 15–24. https://doi.org/10.17509/jem.v13i1.69680
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
Mirjalili, S., Mirjalili, S. M., & Lewis, A. (2014). Grey Wolf Optimizer. Advances in Engineering Software, 69, 46–61. https://doi.org/10.1016/j.advengsoft.2013.12.007
Mubarak, M. N., Susandri, S., Zamsuri, A., & Ramadhani, M. (2025). Pendekatan Wavenet-Inspired Dan LSTM Untuk Prediksi Magnitudo Gempa Sebagai Upaya Transformasi Digital Mitigasi Bencana Di Indonesia. SEMASTER: Seminar Nasional Teknologi Informasi & Ilmu Komputer, 4(1), 368–375.
Nurashila, S. S., Hamami, F., & Kusumasari, T. F. (2023). Perbandingan Kinerja Algoritma Recurrent Neural Network (Rnn) Dan Long Short-Term Memory (Lstm): Studi Kasus Prediksi Kemacetan Lalu Lintas Jaringan Pt Xyz. JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika), 8(3), 864–877. https://doi.org/10.29100/jipi.v8i3.3961
Nurmawati, E., Abaysa, R., & Putra, R. A. (2025). Optimalisasi Portofolio Saham Syariah Berbasis Prediksi Menggunakan Long Short-Term Memory (LSTM). Jurnal Informatika, 10(2).
Paygude, P., Chavan, P., Gayakwad, M., Gupta, K., Joshi, S., Gopika, G., Joshi, R., Gonge, S., & Kotecha, K. (2023). Optimizing Hyperparameters for Enhanced LSTM-Based Prediction System Performance. International Journal on Recent and Innovation Trends in Computing and Communication, 11(10s), 203–213. https://doi.org/10.17762/ijritcc.v11i10s.7620
Purnamasari, S. A. (2025). Mekanisme Perkembangan Pasar Modal Sebagai Salah Satu Produk Investasi di Masyarakat.
Putra, R. A., & Nurmawati, E. (2024). Prediction-based Stock Portfolio Optimization Using Bidirectional Long Short-Term Memory (BiLSTM) and LSTM. Scientific Journal of Informatics, 11(3), 609–620. https://doi.org/10.15294/sji.v11i3.5941
Remetwa, D. P. A., Cahyadi, L., Ferdinand, F. V., Saputra, K. V. I., & Teja, K. (2025). Analysis Of Long Short – Term Memory (Lstm) Parameters In Predicting Ihsg. JOHME: Journal of Holistic Mathematics Education, 9(2), 213–224. (Indonesia). https://doi.org/10.19166/johme.v9i2.10220
Salgotra, R., Sharma, P., Raju, S., & gandomi, A. H. (2024). A Contemporary Systematic Review on Meta-heuristic Optimization Algorithms with Their MATLAB and Python Code Reference. Archives of Computational Methods in Engineering, 31(3), 1749–1822. https://doi.org/10.1007/s11831-023-10030-1
Setiyani, S. H. (2025). Prediksi Pergerakan Harga Saham Menggunakan Quantum Machine Learning Berbasis Variational Quantum Circuits. Jurnal Informatika dan Teknik Elektro Terapan, 13(3S1). https://doi.org/10.23960/jitet.v13i3S1.8038
Song, Y., Chiangpradit, M., & Busababodhin, P. (2025a). Hyperband-Optimized CNN-BiLSTM with Attention Mechanism for Corporate Financial Distress Prediction. Applied Sciences, 15(11), 5934. https://doi.org/10.3390/app15115934
Song, Y., Chiangpradit, M., & Busababodhin, P. (2025b). Hyperband-Optimized CNN-BiLSTM with Attention Mechanism for Corporate Financial Distress Prediction. Applied Sciences, 15(11), 5934. https://doi.org/10.3390/app15115934
Tanjung, M. A., Sari, A. P., & Junaidi, A. (2025). Optimization of LSTM Hyperparameters Using PSO for Forecasting Shallots and Garlic. Bit-Tech, 8(1), 416–426. https://doi.org/10.32877/bt.v8i1.2569
Yosviansyah, M. N., & Rizal, Y. (2024). Optimasi Persediaan Bahan Baku Dan Produksi Usaha Ganepo Putri Yose Dengan Menggunakan Algoritma Grey Wolf Optimizer. MATHunesa: Jurnal Ilmiah Matematika, 12(1), 94–100. https://doi.org/10.26740/mathunesa.v12n1.p94-100
Zhou, W., Liu, S., Guo, J., Liu, N., Li, Z., & Xie, C. (2025). ARIMA-Kriging and GWO-BiLSTM Multi-Model Coupling in Greenhouse Temperature Prediction. Agriculture, 15(8), 900. https://doi.org/10.3390/agriculture15080900
License
Copyright (c) 2026 Eko Budi Pratama, Rudi Nurdiansyah; Muhammad Ali Ridho, Irsyad Khoirun Ramadhan, Ibnu Toharri
This work is licensed under a Creative Commons Attribution 4.0 International License.
Downloads
How to Cite
