Perbandingan Kinerja Model GARCH Dan LSTM Dalam Memprediksi Volatilitas Harian IHSG
DOI:
https://doi.org/10.37859/coscitech.v6i3.10741
Abstract
This study compares the performance of the Generalized Autoregressive Conditional Heteroskedasticity (GARCH) and Long Short-Term Memory (LSTM) models in predicting daily volatility of the Jakarta Composite Index (JCI) for the 2016–2025 period. Volatility is an important indicator in assessing market risk and uncertainty, so accurate prediction methods are needed by investors, analysts, and policymakers. The JCI closing price data is converted into log returns and processed through cleaning, normalization, and sequence formation stages for modeling purposes. The GARCH(1,1) model is used to capture the nature of volatility clustering through a conditional variance approach, while LSTM is utilized to study non-linear patterns and long-term relationships in time series. The results show that GARCH(1,1) is able to describe volatility patterns in general, but is less responsive to sudden changes in volatility. In contrast, the LSTM model provides superior prediction performance with low prediction errors and high coefficient of determination values. These findings indicate that the deep learning approach is more effective in modeling the volatility dynamics of the Jakarta Composite Index (JCI) than traditional econometric methods, especially under volatile market conditions.
Keywords: JCI Volatility, GARCH, LSTM, Time Series Forecasting, Deep Learning
Downloads
References
D. Khalishah et al., “PERBANDINGAN PERFORMA ARIMAX-GARCH DAN LSTM PADA DATA HARGA PENUTUPAN SAHAM PT ANEKA TAMBANG TBK ( ANTM . JK ) COMPARISON OF ARIMAX-GARCH AND LSTM PERFORMANCE ON PT ANEKA TAMBANG TBK ( ANTM . JK ) STOCK CLOSING PRICE DATA,” vol. 12, no. 3, pp. 695–704, 2025.
M. R. Bahtiar, “Volatility Forecasts Jakarta Composite Index ( JCI ) and Index Stock Volatility Sector with Estimated Time Series Volatility Forecasts Jakarta Composite Index ( JCI ) and Index Stock Volatility Sector with Estimated Time Series,” vol. 12, no. 1, 2020, doi: 10.21002/icmr.v12i1.12049.
T. Hutapea, “Analysis of Volatility of the Return of Composite Stock Price Index Using ARCH / GARCH Model , January 2015 - September 2024 Analisis Volatilitas Return Indeks Harga Saham Gabungan ( ISHG ) Memakai Model ARCH / GARCH , Januari 2015 – september 2024,” vol. 7, no. 1, 2025, doi: 10.59806/jkamtb.v7i1.498.
A. A. Tanjung and D. P. Sari, “Analisis Dinamika Volatilitas Indeks Harga Saham Gabungan ( IHSG ): Aplikasi Model Threshold GARCH,” vol. 5, no. 4, pp. 441–447, 2025, doi: 10.47065/jtear.v5i4.2096.
D. A. Adha, A. Ramadhan, H. Maulana, P. P. H. Harahap, and E. Ismanto, “Jurnal Computer Science and Information Technology ( CoSciTech ) Peramalan Harga Emas Berbasis Time Series Menggunakan Arsitektur LSTM Deep Learning Gold Price Forecasting Based on Time Series Using the LSTM Deep Learning Architecture,” vol. 6, no. 2, pp. 329–336, 2025.
W. Jiang, “Applications of deep learning in stock market prediction: recent progress,” pp. 1–97.
L. Wahyuni, S. Abusini, and M. Kurniawaty, “Prediction of Jakarta Composite Index Volatility Using Long Short Term Memory,” no. 04, pp. 32–40, 2022.
A. G. Medina and E. A. Moreno, LSTM – GARCH Hybrid Model for the Prediction of Volatility in Cryptocurrency Portfolios, no. 0123456789. Springer US, 2023. doi: 10.1007/s10614-023-10373-8.
E. Koo and G. Kim, “A Hybrid Prediction Model Integrating GARCH Models With a Distribution Manipulation Strategy Based on LSTM Networks for Stock Market Volatility,” IEEE Access, vol. 10, pp. 34743–34754, 2022, doi: 10.1109/ACCESS.2022.3163723.
K. Kasus, H. Covid-, P. Saham, P. Vaksin, M. Long, and S. M. Lstm, “Jurnal Computer Science and Information Technology ( CoSciTech ),” vol. 6, no. 2, pp. 181–188, 2025.
I. M. A. Dharmaningrat and K. V. I. Saputra, “Predicting the Volatility of Jakarta Composite Index Using GARCH and LSTM with Volume-Up Strategy Approach,” vol. 11, no. 3, pp. 311–322, 2025.
W. Budiharto, “Data science approach to stock prices forecasting in Indonesia during Covid ‑ 19 using Long Short ‑ Term Memory ( LSTM ),” J. Big Data, 2021, doi: 10.1186/s40537-021-00430-0.
S. P. Bhardwaj, R. K. Paul, D. R. Singh, and K. N. Singh, “An Empirical Investigation of Arima and Garch Models in Agricultural Price Forecasting,” vol. 59, no. 3, pp. 415–428, 2014, doi: 10.5958/0976-4666.2014.00009.6.
E. Rafulta, F. Yanuar, D. Devianto, and I. Artikel, “Pemodelan dan Peramalan Volatilitas Memori Panjang pada Return Saham ANTM Studi Komparatif Model GARCH dan,” vol. 5, no. 1, pp. 75–89, 2025.
B. Jange, “Prediksi Volatilitas Indeks Harga Saham Gabungan Menggunakan GARCH,” vol. 4, no. 1, pp. 1–6, 2023, doi: 10.47065/arbitrase.v4i1.1122.
J. Kurniansyah, S. K. Gusti, F. Yanto, and M. Affandes, “Implementasi Model Long Short Term Memory ( LSTM ) dalam Prediksi Harga Saham,” vol. 6, no. 2, pp. 79–86, 2025, doi: 10.47065/bit.v5i2.1783.
D. M. Legawa, M. R. Rizqullah, A. P. Sari, S. P. Prediction, D. Learning, and T. Series, “Penerapan algoritma lstm untuk prediksi harga saham byd”.
