Penerapan LSTM pada Prediksi Harga Saham BBCA: Akurasi dan Interpretabilitas Model

Rara Fazira; Sriani Sriani

doi:10.29408/edumatic.v9i3.32424

Authors

Rara Fazira Program Studi Ilmu Komputer, Universitas Islam Negeri Sumatera Utara
Sriani Sriani Program Studi Ilmu Komputer, Universitas Islam Negeri Sumatera Utara https://orcid.org/0000-0002-4755-7661

DOI:

https://doi.org/10.29408/edumatic.v9i3.32424

Keywords:

deep learning for finance, long short-term memory, model interpretability, stock prediction

Abstract

Financial market instability driven by volatility and stock–bond correlation increases the need for accurate stock price prediction for investment and risk management. Previous deep learning approaches act as black box models with low interpretability, hindering audit and model understanding. The purpose of this study is to analyze the application of the LSTM algorithm to predict the daily closing price of BBCA.JK shares and explain its internal gate mechanism in generating these predictions. The quantitative experimental method uses 1,390 samples (09/19/2019–06/26/2025) from investing.com with 30-, 60-, and 90-day windows. Results show that the 60-day window achieves the lowest RMSE 191.94 and MAE 151.99, while the 30-day window is overly sensitive to short-term fluctuations and the 90-day window retains irrelevant information. The novelty lies in gate-level interpretability analysis, which maps how the forget, input, and output gates manage memory and filter information, addressing black box limitations in prior models. Gate activation analysis shows a positive correlation between the input and output gates and price features, and a negative correlation with volume, representing adaptive information filtering under high market activity. This research expands explainable deep learning in finance and strengthens transparency and model trustworthiness for data-driven investment and risk management.

Author Biography

Sriani Sriani, Program Studi Ilmu Komputer, Universitas Islam Negeri Sumatera Utara

Lecturer of Computer Science at the State Islamic University of North Sumatra

References

Astudillo, K., Flores, M., Soliz, M., Ferreira, G., & Varela-Aldás, J. (2025). A Hybrid GAS-ATT-LSTM Architecture for Predicting Non-Stationary Financial Time Series. Mathematics, 13(14), 1–29. https://doi.org/10.3390/math13142300

Attaulah, D. T., & Soyusiawaty, D. (2025). Analisis Sentimen Program Makan Siang Gratis di Twitter/X menggunakan Metode BI-LSTM. Edumatic: Jurnal Pendidikan Informatika, 9(1), 294–303. https://doi.org/10.29408/edumatic.v9i1.29725

Beniwal, M., Singh, A., & Kumar, N. (2023). Forecasting long-term stock prices of global indices: A forward-validating Genetic Algorithm optimization approach for Support Vector Regression. Applied Soft Computing, 145(9), 1–19. https://doi.org/10.1016/j.asoc.2023.110566

Bolboacă, R., & Haller, P. (2024). Enhanced long short-term memory architectures for chaotic systems modeling: An extensive study on the Lorenz system. Chaos, 34(12), 1–22. https://doi.org/10.1063/5.0238619

Bustos, O., Pomares-Quimbaya, A., & Stellian, R. (2025). Machine learning, stock market forecasting, and market efficiency: a comparative study. International Journal of Data Science and Analytics, 20(7), 6815–6839. https://doi.org/10.1007/s41060-025-00854-4

Černevičienė, J., & Kabašinskas, A. (2024). Explainable artificial intelligence (XAI) in finance: a systematic literature review. Artificial Intelligence Review, 57(8), 1–45. https://doi.org/10.1007/s10462-024-10854-8

Firouzjaee, J. T., & Khalilian, P. (2024). The Interpretability of LSTM Models for Predicting Oil Company Stocks: Impact of Correlated Features. International Journal of Energy Research, 2024(47), 1–18. https://doi.org/10.1155/2024/5526692

Giudici, P., Piergallini, A., Recchioni, M. C., & Raffinetti, E. (2024). Explainable Artificial Intelligence methods for financial time series. Physica A: Statistical Mechanics and Its Applications, 655(12), 1–14. https://doi.org/10.1016/j.physa.2024.130176

Hartono, P. C., & Widiantoro, A. D. (2024). Analisis Prediksi Harga Saham Unilever Menggunakan Regresi Linier dengan RapidMiner. Journal of Computer and Information Systems Ampera, 5(3), 2496–2775.

Hastomo, W., Karno, A. S. B., Kalbuana, N., Nisfiani, E., & ETP, L. (2021). Optimasi Deep Learning untuk Prediksi Saham di Masa Pandemi Covid-19. Jurnal Edukasi Dan Penelitian Informatika (JEPIN), 7(2), 133–140. https://doi.org/10.26418/jp.v7i2.47411

Kong, Y., Wang, Z., Nie, Y., Zhou, T., Zohren, S., Liang, Y., Sun, P., & Wen, Q. (2025). Unlocking the Power of LSTM for Long Term Time Series Forecasting. Applied Operations and Analytics (AOA, 39(8), 11968–11976. https://doi.org/10.48550/arXiv.2408.10006

Kusuma, N. P. N. (2024). Prediksi Harga Saham Blue Chip Pada Indeks Idx30 Menggunakan Algoritma Recurrent Neural Network (RNN). Jurnal Ekonomi & Bisnis, 23(1), 90–97. https://doi.org/https://doi.org/10.32722/eb.v23i1.6609

Fuente, L. A. D. la, Ehsani, M. R., Gupta, H. V., & Condon, L. E. (2024). Toward interpretable LSTM-based modeling of hydrological systems. Hydrology and Earth System Sciences, 28(4), 945–971. https://doi.org/10.5194/hess-28-945-2024

Li, Q., Kamaruddin, N., Yuhaniz, S. S., & Al-Jaifi, H. A. A. (2024). Forecasting stock prices changes using long-short term memory neural network with symbolic genetic programming. Scientific Reports, 14(1), 1–24. https://doi.org/10.1038/s41598-023-50783-0

Mahmoudi, A. (2025). Investigating LSTM-based time series prediction using dynamic systems measures. Evolving Systems, 16(2), 1–18. https://doi.org/10.1007/s12530-025-09703-y

Mariam, S., & Nurhaida, I. (2025). Analisis Sentimen berbasis Deep Learning Terhadap Kesetaraan Gender di Bidang STEM: Perspektif dan Implikasinya. Edumatic: Jurnal Pendidikan Informatika, 9(1), 69–78. https://doi.org/10.29408/edumatic.v9i1.29071

Muhammad, D., Ahmed, I., Naveed, K., & Bendechache, M. (2024). An explainable deep learning approach for stock market trend prediction. Heliyon, 10(21), 1–15. https://doi.org/10.1016/j.heliyon.2024.e40095

Muhidin, A., Rilvani, E., & Naya, C. (2025). Model Hybird Fuzzy Logic dan Deep Learning untuk Prediksi Harga Saham. Edumatic : Jurnal Pendidikan Informatika, 9(2), 522–531. https://doi.org/10.29408/edumatic.v9i2.30890

Radfar, E. (2025). Stock market trend prediction using deep neural network via chart analysis: a practical method or a myth? Humanities and Social Sciences Communications, 12(1), 1–10. https://doi.org/10.1057/s41599-025-04761-8

Rahmadeyan, A., & Mustakim. (2024). Long Short-Term Memory and Gated Recurrent Unit for Stock Price Prediction. Procedia Computer Science, 234(1), 204–212. https://doi.org/10.1016/j.procs.2024.02.167

Wang, C., Li, Y., Sun, X., Wu, Q., Wang, D., & Huang, Z. (2023). DeLELSTM: Decomposition-based Linear Explainable LSTM to Capture Instantaneous and Long-term Effects in Time Series. International Joint Conferences on Artificial Intelligence, 32(8), 4299–4307. https://doi.org/10.24963/ijcai.2023/478

Waqas, M., & Humphries, U. W. (2024). A critical review of RNN and LSTM variants in hydrological time series predictions. MethodsX, 13(2), 1–19. https://doi.org/10.1016/j.mex.2024.102946

Weber, P., Carl, K. V., & Hinz, O. (2024). Applications of Explainable Artificial Intelligence in Finance—a systematic review of Finance, Information Systems, and Computer Science literature. Management Review Quarterly, 74(2), 867–907. https://doi.org/10.1007/s11301-023-00320-0

Zhang, Z., Wang, D., Mei, Y., Zhu, J., & Xiao, X. (2025). Developing an explainable deep learning module based on the LSTM framework for flood prediction. Frontiers in Water, 7(5), 1–6. https://doi.org/10.3389/frwa.2025.1562842