Hybrid EGARCH-LSTM for Price Forecasting and Risk Estimation of Daily USD/IDR (2015–2025)
DOI:
https://doi.org/10.47065/bulletincsr.v6i1.884Keywords:
Time Series; EGARCH; LSTM; Hybrid Model; Value at Risk (VaR)Abstract
Forecasting volatility in the USD/IDR exchange rate poses a critical challenge for Indonesia's financial stability, especially given how the data tends to display non-linear characteristics along with extreme outliers—what we commonly call fat-tails. This research develops a hybrid EGARCH-LSTM architecture to address these challenges by bringing together the precision of econometric modeling with deep learning's adaptability. Our dataset consists of 2,605 daily observations of the USD to IDR exchange rate ranging from 2015 to 2025. We extract volatility features using an EGARCH(1, 1) model with a t-distribution, which will then be entered as exogenous input into a Long-Short-Term Memory (LSTM) network. Our analysis shows a strong contrast between price predictions and risk estimates. In terms of price forecasting, the market demonstrates remarkable efficiency. The simple Naive Forecast, with an RMSE of 100.47, proved extremely difficult to outperform, lending support to the Random Walk Hypothesis. However, the Hybrid EGARCH-LSTM demonstrated superior volatility prediction capabilities, achieving the lowest Out-of-Sample Volatility MAE of 0.0075 compared to 0.0083 for the standalone EGARCH model. The EGARCH-LSTM hybrid model achieved the best performance, passed the Kupiec backtest (P-value = 0.4373), and significantly outperformed the pure econometric model, which failed due to excessive conservatism in its estimation. This study concludes that although accurate price predictions are still unattainable in efficient markets, the EGARCH-LSTM hybrid architecture provides a powerful and reliable tool for risk estimation. These results offer significant implications for hedging and risk management practices in the Indonesian foreign exchange market.
Downloads
References
M. Bosupeng, A. Naranpanawa, and J. J. Su, “Does exchange rate volatility affect the impact of appreciation and depreciation on the trade balance? A nonlinear bivariate approach,” Econ Model, vol. 130, Jan. 2024, doi: 10.1016/j.econmod.2023.106592.
A. Kartono, M. Febriyanti, S. T. Wahyudi, and Irmansyah, “Predicting foreign currency exchange rates using the numerical solution of the incompressible Navier–Stokes equations,” Physica A: Statistical Mechanics and its Applications, vol. 560, Dec. 2020, doi: 10.1016/j.physa.2020.125191.
N. N. AlMadany, O. Hujran, G. Al Naymat, and A. Maghyereh, “Forecasting cryptocurrency returns using classical statistical and deep learning techniques,” International Journal of Information Management Data Insights, vol. 4, no. 2, Nov. 2024, doi: 10.1016/j.jjimei.2024.100251.
N. Nengah et al., “(print) JSIKTI: Jurnal Sistem Informasi dan Komputer terapan Indonesia Deep Learning Approach for USD to IDR Forecasting with LSTM Deep Learning Approach for USD to IDR Forecasting with LSTM "Deep Learning Approach for USD to IDR Forecasting with LSTM,” JSIKTI: Jurnal Sistem Informasi dan Komputer Terapan Indonesia, vol. 8, no. 1, pp. 91–100, 2025, [Online]. Available: www.infoteks.orgJournalPageisavailabletohttps://infoteks.org/journals/index.php/jsikti
E. Verianto and A. F. Shimbun, “TRANSFORMER WITH LAGGED FEATURES FOR HANDLING LONG-TERM DATA DEPENDENCY IN TIME SERIES FORECASTING,” JIKO (Jurnal Informatika dan Komputer), vol. 7, no. 3, pp. 232–241, Dec. 2024, doi: 10.33387/jiko.v7i3.9247.
E. Nsengiyumva, J. K. Mung’atu, and C. Ruranga, “Hybrid GARCH-LSTM Forecasting for Foreign Exchange Risk,” FinTech, vol. 4, no. 2, Jun. 2025, doi: 10.3390/fintech4020022.
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.
C. S. Huang and A. Sayed, “Novel forecasting of white maize futures volatility: a hybrid GARCH-based bi-directional LSTM model,” Cogent Economics and Finance, vol. 13, no. 1, 2025, doi: 10.1080/23322039.2025.2484422.
W. Nhlapho, M. Atemkeng, and J. C. Ndogmo, “An attention-guided hybrid statistical and deep learning modeling for enhanced time series forecasting: A case study of South African telecommunication companies,” Sci Afr, vol. 30, Dec. 2025, doi: 10.1016/j.sciaf.2025.e02950.
Z. Guo, “Research on the Augmented Dickey-Fuller Test for Predicting Stock Prices and Returns,” Advances in Economics, Management and Political Sciences, vol. 44, no. 1, pp. 101–106, Nov. 2023, doi: 10.54254/2754-1169/44/20232198.
J. R. Porto de Carvalho, E. D. Assad, A. F. de Oliveira, and H. Silveira Pinto, “Annual maximum daily rainfall trends in the midwest, southeast and southern Brazil in the last 71 years,” 2014, Elsevier B.V. doi: 10.1016/j.wace.2014.10.001.
H. Malmsten and T. Terasvirta, “Stylized Facts of Financial Time Series and Three Popular Models of Volatility,” vol. 3, Sep. 2004.
T. Thadewald and H. Büning, “Jarque–Bera Test and its Competitors for Testing Normality – A Power Comparison,” J Appl Stat, vol. 34, no. 1, pp. 87–105, Jan. 2007, doi: 10.1080/02664760600994539.
R. F. Engle, “Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation,” Econometrica, vol. 50, no. 4, pp. 987–1007, 1982, doi: 10.2307/1912773.
J. C. Smolovi?, M. L. Božovi?, and S. Vujoševi?, “GARCH models in value at risk estimation: Empirical evidence from the montenegrin stock exchange,” Economic Research-Ekonomska Istrazivanja , vol. 30, no. 1, pp. 477–498, Apr. 2017, doi: 10.1080/1331677X.2017.1305773.
N. Godfrey Emenogu, “Selecting superior GARCH model with backtesting approach in First Bank of Nigeria stock returns,” 2023. [Online]. Available: https://www.researchgate.net/publication/378139201
H. Hassani and M. Yeganegi, “Selecting optimal lag order in Ljung–Box test,” Physica A: Statistical Mechanics and its Applications, vol. 541, p. 123700, Dec. 2019, doi: 10.1016/j.physa.2019.123700.
C. Fjellström, “Long Short-Term Memory Neural Network for Financial Time Series,” Jan. 2022, [Online]. Available: http://arxiv.org/abs/2201.08218
C. C. Islamy and A. Wahabi, “Sistemasi: Jurnal Sistem Informasi Perbandingan Model LSTM dan GRU untuk Peramalan Angin A Comparative Study of LSTM and GRU Models for Wind Forecasting.” [Online]. Available: http://sistemasi.ftik.unisi.ac.id
J. Liu, “A Hybrid Model Integrating LSTM with Multiple GARCH-Type Models for Volatility and Var Forecast,” European Alliance for Innovation n.o., Jun. 2023. doi: 10.4108/eai.6-1-2023.2330313.
K. Xu, Y. Wu, M. Jiang, W. Sun, and Z. Yang, “Hybrid LSTM-GARCH Framework for Financial Market Volatility Risk Prediction,” 2024. [Online]. Available: https://www.mfacademia.org/index.php/jcssa
S. Stevenson, “A Comparison of the Forecasting Ability of ARIMA Models,” Journal of Property Investment & Finance, vol. 25, pp. 223–240, May 2007, doi: 10.1108/14635780710746902.
C. Zhang, “Movement Prediction-Adjusted Naive Forecast: Is the Naive Baseline Unbeatable in Financial Time Series Forecasting?,” Oct. 2025, [Online]. Available: http://arxiv.org/abs/2406.14469
K. Kladívko and P. Österholm, “Do market participants’ forecasts of financial variables outperform the random-walk benchmark?,” Financ Res Lett, vol. 40, p. 101712, 2021, doi: https://doi.org/10.1016/j.frl.2020.101712.
J. He, “Capturing Four Stylized Facts of Financial Time Series in GARCH and Stochastic Volatility Models,” 2020. doi: 10.23977/ICEMGD2020.051.
D. Kim and M. Shin, “Volatility models for stylized facts of high-frequency financial data,” J Time Ser Anal, vol. 44, no. 3, pp. 262–279, May 2023, doi: https://doi.org/10.1111/jtsa.12666.
L. N. A. Mualifah, A. M. Soleh, and K. A. Notodiputro, “Comparison of GARCH, LSTM, and Hybrid GARCH-LSTM Models for Analyzing Data Volatility,” International Journal of Advances in Soft Computing and its Applications, vol. 16, no. 2, pp. 150–165, 2024, doi: 10.15849/IJASCA.240730.10.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Hybrid EGARCH-LSTM for Price Forecasting and Risk Estimation of Daily USD/IDR (2015–2025)
ARTICLE HISTORY
How to Cite
Issue
Section
Copyright (c) 2025 Alfaiz Arifin Setia Budi, Siti Salsabila Maryanto, Muhammad Althafino, Salsabila Sekar Nadia, Zulvania Armiana, Shaifudin Zuhdi
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
