Perbandingan Performa Model GARCH, LSTM dan Hybrid untuk Prediksi Harga Saham Syariah JII

Shynde Limar Kinanti; Intan Rozana

doi:10.31004/riggs.v4i3.3109

Authors

Shynde Limar Kinanti Universitas Bina Sarana Informatika
Intan Rozana Universitas Bina Sarana Informatika

DOI:

https://doi.org/10.31004/riggs.v4i3.3109

Keywords:

prediksi harga saham, harga saham syariah, GARCH, LSTM, hybrid model

Abstract

Pasar saham syariah di Indonesia menunjukkan pertumbuhan yang pesat seiring meningkatnya minat masyarakat terhadap investasi berbasis prinsip Islam. Namun demikian, harga saham syariah bersifat fluktuatif sehingga untuk melakukan prediksi harga saham menjadi sebuah tantangan. Penelitian ini bertujuan untuk membandingkan performa model GARCH, LSTM, dan model hybrid GARCH–LSTM dalam memprediksi harga saham. Data yang digunakan adalah data harga saham syariah dari Jakarta Islamic Index (JII) yaitu salah satu indeks saham yang ada di Indonesia yang menghitung index harga rata-rata saham untuk jenis saham-saham yang memenuhi kriteria syariah. Data diambil dalam periode 5 tahun sejak 1 September 2019 hingga 31 Agustus 2025. Evaluasi model berdasarkan nilai Root Mean Square Error (RMSE) dan Mean Absolute Percentage Error (MAPE), model hybrid menunjukkan performa terbaik dengan RMSE sebesar 6.85 dan MAPE 1.10%, jauh lebih rendah dibandingkan model GARCH (RMSE 41.45; MAPE 6.79%) maupun LSTM (RMSE 39.81; MAPE 6.67%). Hal ini menunjukkan bahwa integrasi volatilitas dari GARCH ke dalam struktur pembelajaran LSTM secara signifikan meningkatkan akurasi dan stabilitas hasil prediksi. Model hybrid berhasil mengatasi kelemahan masing-masing model tunggal, dengan menggabungkan kemampuan GARCH dalam menangkap volatilitas serta keunggulan LSTM dalam mempelajari pola non-linear dan jangka panjang.

Downloads

Download data is not yet available.

References

M. Wandira and W. Saputra, “Determinan perubahan stock price volatility pada perusahaan LQ45,” Jurnal Akuntansi Bisnis, vol. 16, no. 2, 2023. doi: 10.30813/jab.v16i2.4328

M. I. Zulkarnaen, W. Wartoyo, and A. Sudrajat, “Determinan Indeks Harga Saham Syariah di Jakarta Islamic Index (JII) periode 2019–2023,” Journal of Contemporary Sharia Economics, vol. 3, no. 3, 2023. doi: 10.59188/jcs.v3i3.642

S. Ayu, “Merespons volatilitas global: Strategi penguatan pasar modal syariah Indonesia,” Journal of Shariah and Islamic Finance, vol. 4, no. 1, 2023. doi: 10.47902/jshi.v4i1.391

T. Bollerslev, “Generalized autoregressive conditional heteroskedasticity,” Journal of Econometrics, vol. 31, no. 3, pp. 307–327, 1986. doi: 10.1016/0304-4076(86)90063-1

B. Hartanto, “Analisis prediksi Indeks Saham Syariah Indonesia (ISSI) menggunakan metode GARCH,” Ekonomika 45: Jurnal Ilmu Ekonomi dan Bisnis, vol. 10, no. 1, 2023. doi: 10.30640/ekonomika45.v10i1.893

P. R. Hansen and A. Lunde, “A forecast comparison of volatility models: Does anything beat a GARCH(1,1)?,” Journal of Applied Econometrics, vol. 20, no. 7, pp. 873–889, 2005. doi: 10.1002/jae.800

D. G. McMillan and A. E. H. Speight, “Daily volatility forecasts: Reassessing the performance of GARCH models,” International Journal of Forecasting, vol. 20, no. 1, pp. 101–117, 2004. doi: 10.1016/j.ijforecast.2003.08.004

I. Boudri and A. El Bouhadi, “Modeling and forecasting historical volatility using econometric and deep learning approaches,” Journal of Risk and Financial Management, vol. 17, no. 7, p. 300, 2024. doi: 10.3390/jrfm17070300

D. K. T. Suwarso et al., “Perbandingan performa ARIMAX-GARCH dan LSTM pada data harga penutupan saham PT Aneka Tambang Tbk (ANTM.JK),” Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 12, no. 8, 2025. doi: 10.25126/jtiik.2025128756

S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997. doi: 10.1162/neco.1997.9.8.1735

T. Fischer and C. Krauss, “Deep learning with long short-term memory networks for financial market predictions,” European Journal of Operational Research, vol. 270, no. 2, pp. 654–669, 2018. doi: 10.1016/j.ejor.2017.11.054

D. M. Q. Nelson, A. C. M. Pereira, and R. A. de Oliveira, “Stock market’s price movement prediction with LSTM neural networks,” in Proc. 2017 International Joint Conference on Neural Networks (IJCNN), pp. 1419–1426, 2017. doi: 10.1109/IJCNN.2017.7966019

W. Bao, J. Yue, and Y. Rao, “A deep learning framework for financial time series using stacked autoencoders and long short-term memory,” PLOS ONE, vol. 12, no. 7, e0180944, 2017. doi: 10.1371/journal.pone.0180944

R. S. Tsay, Analysis of Financial Time Series, 3rd ed., Wiley, 2010.

C. Bircanoğlu and N. Arıca, “A comparison of activation functions in artificial neural networks,” in Proc. 2018 26th Signal Processing and Communications Applications Conf. (SIU), pp. 1–4, 2018. doi: 10.1109/SIU.2018.8404330

S. Sharma, S. Sharma, and A. Athaiya, “Activation functions in neural networks,” Towards Data Science, vol. 6, pp. 310–316, 2017.

A. J. Dautel, W. K. Härdle, S. Lessmann, and H. V. Seow, “Forex exchange rate forecasting using deep recurrent neural networks,” Digital Finance, vol. 2, pp. 69–96, 2020. doi: 10.1007/s42521-020-00017-0

E. Nsengiyumva, J. K. Mung’atu, and C. Ruranga, “Hybrid GARCH–LSTM forecasting for foreign exchange risk,” FinTech, vol. 4, no. 2, p. 22, 2025. doi: 10.3390/fintech4020022

L. Zhang, C. Aggarwal, and Y. Qi, “Stock price prediction using LSTM neural network,” Procedia Computer Science, vol. 174, pp. 75–82, 2020. doi: 10.1016/j.procs.2020.06.014

M. A. Maricar, P. Widiadnyana, and W. A. Wijaya, “Analysis of data mining for forecasting total goods delivery with moving average method,” International Journal of Engineering and Emerging Technology, vol. 2, no. 1, pp. 7–10, 2017.