Analisis Komparatif Kinerja LSTM, BiLSTM, dan LSTM-AM dalam Prediksi Harga Saham Syariah
Abstract
The continuously evolving Sharia stock market necessitates more accurate price modeling due to high volatility, regime shifts, and outliers that frequently disrupt investment decision-making processes. This study aims to comparatively evaluate the performance of three deep learning algorithms—LSTM (Long Short-Term Memory), BiLSTM (Bidirectional LSTM), and LSTM-AM (LSTM with Attention Mechanism)—in predicting Sharia stock prices. The research method utilizes daily closing price data from five Indonesian Sharia-compliant issuers (ANTM, ERAA, KLBF, SMGR, and WIKA) spanning the period of December 2016 to December 2021. The data underwent preprocessing using Robust Scaling and was structured into time series with a 60-day window. Model evaluation was conducted via window-based cross-validation with the results show that BiLSTM delivered the best performance with an average MAPE of 9.41% and RMSE of 249.956. This performance was followed by LSTM (MAPE 11.87%) and LSTM-AM as the lowest (MAPE 19.58%). These findings provide a clear understanding of the effectiveness of each architecture in predicting dynamic Sharia stock prices, indicating that increasing model complexity (LSTM-AM) does not always guarantee better accuracy in this domain. Consequently, BiLSTM can be considered the superior model for more stable prediction.
Downloads
References
[2] Zamaluddin, Rochim, A., Andatu, M., Saputra, R., 2023, Hukum Jual Beli Saham BRIS di Komunitas Syariah Saham dalam Perspektif Hukum Islam dan Positif, Mandub: Jurnal Politik, Sosial, Hukum dan Humaniora, Vol. 1, No. 4, Indonesia
[3] Khuwaja, P., Khowaja, S. A., Khoso, I., Lashari, I. A., 2020, Prediction of Stock Movement Using Phase Space Reconstruction and Extreme Learning Machines, Journal of Experimental and Theoretical Artificial Intelligence, Vol. 32, No. 1, Taylor & Francis, United Kingdom
[4] Kong, X., et al., 2025, Deep Learning for Time Series Forecasting: A Survey, International Journal of Machine Learning and Cybernetics, Springer, Germany
[5] Cho, K., Kim, Y., 2022, Improving Streamflow Prediction in the WRF-Hydro Model with LSTM Networks, Journal of Hydrology, Vol. 605, Elsevier, Netherlands
[6] Chen, N., 2024, Exploring the Development and Application of LSTM Variants, Applied and Computational Engineering, Vol. 53, No. 1, United States
[7] Pham, T. D., 2021, Time–Frequency Time–Space LSTM for Robust Classification of Physiological Signals, Scientific Reports, Vol. 11, Nature Publishing Group, United Kingdom
[8] Budiprasetyo, G., Hani’ah, M., Aflah, D., 2023, Prediksi Harga Saham Syariah Menggunakan Algoritma Long Short-Term Memory (LSTM), Jurnal Nasional Teknologi dan Sistem Informasi, Vol. 8, Indonesia
[9] Mahajan, R., Mansotra, V., 2021, Predicting Geolocation of Tweets Using Combination of CNN and BiLSTM, Data Science and Engineering, Vol. 6, No. 4, Springer, Singapore
[10] Feng, Z., Hu, X., Tian, Z., Jiang, B., Zhang, H., Zhang, W., 2023, Bi-LSTM-Based Dynamic Prediction Model for Pulling Speed of Czochralski Single-Crystal Furnace, Journal of Computing and Information Science in Engineering, Vol. 23, No. 4, ASME, United States
[11] Puteri, D., 2023, Implementasi Long Short Term Memory (LSTM) dan Bidirectional Long Short Term Memory (BiLSTM) dalam Prediksi Harga Saham Syariah, Euler: Jurnal Ilmiah Matematika, Sains dan Teknologi, Vol. 11, Indonesia
[12] Fang, W., Zhuo, W., Yan, J., Song, Y., Jiang, D., Zhou, T., 2022, Attention Meets Long Short-Term Memory: A Deep Learning Network for Traffic Flow Forecasting, Physica A: Statistical Mechanics and Its Applications, Vol. 587, Elsevier, Netherlands
[13] Lu, S., Liu, M., Yin, L., Yin, Z., Liu, X., Zheng, W., 2023, The Multi-Modal Fusion in Visual Question Answering: A Review of Attention Mechanisms, PeerJ Computer Science, Vol. 9, United States
[14] Zou, Z., Yan, X., Yuan, Y., You, Z., Chen, L., 2024, Attention Mechanism Enhanced LSTM Networks for Latency Prediction in Deterministic MEC Networks, Intelligent Systems with Applications, Vol. 23, Elsevier, Netherlands
[15] Shen, J., Shafiq, M. O., 2020, Short-Term Stock Market Price Trend Prediction Using a Comprehensive Deep Learning System, Journal of Big Data, Vol. 7, Springer, United Kingdom
[16] Taufik, R., Aristoteles, A., Ilman, I. S., 2025, A Hybrid Model to Mitigate Data Gaps and Fluctuations in Tax Revenue Forecasting, International Journal of Electrical and Computer Engineering, Vol. 15, No. 4, Indonesia
[17] Schechtman, E., Shelef, A., 2018, Correlation and the Time Interval over Which the Variables Are Measured: A Non-Parametric Approach, PLOS ONE, Vol. 13, No. 11, United States
[18] Pratiwi, N., Rosadi, D., Abdurakhman, 2025, Robust Scaling Strategies for Outlier Handling in Orthogonal Projection to Latent Structures Discriminant Analysis (OPLS-DA), Communications in Statistics Simulation and Computation, Vol. 54, No. 5, United Kingdom
[19] Bhandari, H. N., Rimal, B., Pokhrel, N. R., Rimal, R., Dahal, K. R., Khatri, R. K. C., 2022, Predicting Stock Market Index Using LSTM, Machine Learning with Applications, Vol. 9, Elsevier, United Kingdom
[20] Agarwal, S., Sharma, S., Faisal, K. N., Sharma, R. R., 2025, Time-Series Forecasting Using SVMD-LSTM: A Hybrid Approach for Stock Market Prediction, Journal of Probability and Statistics, Vol. 2025, United Kingdom
[21] Phuoc, T., Anh, P. T. K., Tam, P. H., Nguyen, C. V., 2024, Applying Machine Learning Algorithms to Predict the Stock Price Trend in the Stock Market: The Case of Vietnam, Humanities and Social Sciences Communications, Vol. 11, United Kingdom
[22] Bergstra, J., Bengio, Y., 2012, Random Search for Hyper-Parameter Optimization, Journal of Machine Learning Research, Vol. 13, United States
[23] Vilares F. M., Doval Mosquera, Y., Ribadas P. F. J., Darriba B., V. M., 2023, Early Stopping by Correlating Online Indicators in Neural Networks, Neural Networks, Vol. 159, Elsevier, Netherlands
[24] Bergmeir, C., Benítez, J. M., 2012, On the Use of Cross-Validation for Time Series Predictor Evaluation, Information Sciences, Vol. 191, Elsevier, Netherlands
[25] Hodson, T. O., 2022, Root-Mean-Square Error (RMSE) or Mean Absolute Error (MAE): When to Use Them or Not, Geoscientific Model Development, Vol. 15, No. 14, Germany
[26] Colton, J., Bower, K., 2002, Some Misconceptions about R-Square, Statistical Review, Vol. 3, United States
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Open Access Policy
This is an open-access journal which means that all content is freely available without charge to the users or their institution. Users are allowed to read, download, copy, distribute, print, search, or link to the full texts of the articles, or use them for any other lawful purpose, without asking prior permission from the publisher or the author. This is in accordance with the BOAI definition of open access.
This work is licensed under Creative Commons Attribution-ShareAlike 4.0 International
