Penerapan Algoritma Long Short-Term Memory pada Prediksi Harga Saham Harian PT Bank Syariah Indonesia (BRIS)
DOI:
https://doi.org/10.32670/dej.v2i2.22Keywords:
Deep Learning, LSTM, BRIS, Sliding WindowAbstract
Fluktuasi harga saham yang dinamis dan nonlinear menjadi tantangan besar dalam manajemen risiko investasi, khususnya pada sektor perbankan syariah yang perkembangannya kian akseleratif. Penelitian ini bertujuan untuk memprediksi harga penutupan (close price) harian saham PT Bank Syariah Indonesia Tbk (BRIS) dengan pendekatan kecerdasan buatan berbasis jaringan saraf tiruan Long Short-Term Memory (LSTM). Data historis sekuensial bersumber dari Investing.com ditransformasikan ke dalam format supervised learning melalui rekayasa fitur jendela bergeser (sliding window) berukuran 3 hari (t-3, t-2, t-1), dengan rentang nilai batas ekstrem Rp1.100 hingga Rp3.160. Dataset dibagi secara kronologis dengan rasio 80% untuk data pelatihan dan 20% untuk data pengujian. Hasil pengujian empiris menunjukkan bahwa model komputasi LSTM yang dibangun mampu melacak arah pergerakan tren dengan sangat presisi dan menghasilkan tingkat galat yang minim, ditunjukkan oleh perolehan nilai Mean Absolute Error (MAE) sebesar Rp50,09. Penelitian ini secara ilmiah membuktikan ketangguhan arsitektur LSTM dalam mengatasi masalah vanishing gradient dan keterbatasan model statistik linear konvensional, sehingga sangat andal direkomendasikan sebagai sistem pendukung keputusan yang akurat bagi para investor dalam melakukan perdagangan saham jangka pendek.
References
Alkahfi, C., Kurnia, A., & Saefuddin, A. (2024). Perbandingan Kinerja Model Berbasis RNN pada Peramalan Data Ekonomi dan Keuangan Indonesia. MALCOM: Indonesian Journal of Machine Learning and Computer Science, 4(4), 1235–1243. https://doi.org/10.57152/malcom.v4i4.1415
Arsi, P., Astuti, T., Rahmawati, D., & Subarkah, P. (2022). Implementasi Sliding Window Algotihm pada Prediksi Kurs berbasis Neural Network. DoubleClick: Journal of Computer and Information Technology, 6(1), 51. https://doi.org/10.25273/doubleclick.v6i1.13496
Bao, W., Yue, J., & Rao, Y. (2017). A deep learning framework for financial time series using stacked autoencoders and long-short term memory. PLOS ONE, 12(7), e0180944. https://doi.org/10.1371/journal.pone.0180944
Bengio, Y., Simard, P., & Frasconi, P. (1994). Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks, 5(2), 157–166. https://doi.org/10.1109/72.279181
Dietterich, T. G. (2002). Machine Learning for Sequential Data: A Review (pp. 15–30). https://doi.org/10.1007/3-540-70659-3_2
Fischer, T., & Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research, 270(2), 654–669. https://doi.org/10.1016/j.ejor.2017.11.054
Goodfellow, Ian., Bengio, Yoshua., & Courville, Aaron. (2017). Deep learning. The MIT Press.
Han, Jiawei., Kamber, Micheline., & Pei, Jian. (2012). Data mining : concepts and techniques. Elsevier/Morgan Kaufmann.
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
investing.com. (2026). Data Historis BRIS.
Navila, I., Nada, N. Q., & Renaldy, R. (2026). Banking Stock Price Prediction Dashboard Using Long Short-Term Memory. Jurnal Teknik Informatika (Jutif), 7(2), 2008–2022. https://doi.org/10.52436/1.jutif.2026.7.2.5802
Noer Azam Achsani, Linda Karlina Sari, Ade Holis, Bayu Bandono, & Gandhi Cahyo Wicaksono. (2025). Asymmetric Volatility Spillover and Risk Contagion During the COVID-19 Outbreak: Empirical Investigation from the Indonesian and Global Stock Markets. Advanced and Sustainable Technologies (ASET), 4(2), 262–275. https://doi.org/10.58915/aset.v4i2.2695
Novita, S., Ruhadi, & Syarief, Moch. E. (2020). Determinants of Dividend Policy in Jakarta Islamic Index (JII) Companies. Proceedings of the International Seminar of Science and Applied Technology (ISSAT 2020). https://doi.org/10.2991/aer.k.201221.103
Pangestika, Z., & Josaphat, B. P. (2025). Predicting Stock Price Using Convolutional Neural Network and Long Short Term Memory (Case Study: Stock of BBCA). Journal of the Indonesian Mathematical Society, 31(1), 1512. https://doi.org/10.22342/jims.v31i1.1512
Pascanu, R., Mikolov, T., & Bengio, Y. (2013). On the difficulty of training Recurrent Neural Networks.
Robiyanto, R. (2018). Indonesian Stock Market’s Dynamic Integration with Asian Stock Markets and World Stock Markets. Jurnal Pengurusan, 52, 181–192. https://doi.org/10.17576/pengurusan-2018-52-15
Yudistira, N., Alfiansih, L. M. D., Andriyani, N. I., Essayem, W., Maulida, N., Maghfiroh, N. A., & Nurdian, I. W. (2023). Prediksi Deret Waktu Menggunakan Deep Learning. UB Press.
Zhang, G. P. (2003). Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 50, 159–175. https://doi.org/10.1016/S0925-2312(01)00702-0
