Comparative Deep Learning Models for Indonesian Gold Price Forecasting
Advance Sustainable Science Engineering and Technology · 24.05.2026 · 8 (3) · 0260301
DOI: 10.26877/asset.v8i3.2608 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advance Sustainable Science Engineering and Technology, online erschienen am 24.05.2026. Verfasst von Albi Pernata Jomantara Putra und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).
Abstract (Originalsprache)
This study evaluates LSTM, CNN-LSTM, LSTM-GRU, and CNN-LSTM-GRU architectures for forecasting Indonesian gold prices using 1,269 daily observations (2022–2025). Models utilized Bayesian-optimized hyperparameters and were benchmarked against ARIMA-GARCH and Random Forest baselines across 30-day and 365-day horizons. Performance was assessed via MAE, RMSE, R², and MAPE, confirming deep learning’s superiority in capturing non-linear dynamics over classical methods. The LSTM-GRU achieved the best numerical results, with MAPEs of 1.21% (short-term) and 1.32% (long-term). However, qualitative evaluation revealed that the highest-scoring model produced unstable long-term predictions, indicating a critical trade-off between numerical accuracy and forecast realism. These findings suggest financial model selection must prioritize stability alongside statistical metrics. A key limitation is the exclusive use of univariate data, necessitating future multivariate validation with macroeconomic indicators.
Zitieren
APA
Putra, A. P. J., Williamsyah, B. M., Rizal, A., Dewanta, F., Prasasti, A. L., & Ziani, S. (2026). Comparative Deep Learning Models for Indonesian Gold Price Forecasting. Advance Sustainable Science Engineering and Technology, 8(3), 0260301. https://doi.org/10.26877/asset.v8i3.2608
Vancouver
Putra APJ, Williamsyah BM, Rizal A, Dewanta F, Prasasti AL, Ziani S. Comparative Deep Learning Models for Indonesian Gold Price Forecasting. Advance Sustainable Science Engineering and Technology. 2026;8(3):0260301. doi:10.26877/asset.v8i3.2608
BibTeX
@article{Putra2026,
author = {Putra, Albi Pernata Jomantara and Williamsyah, Baginda Mi’raj and Rizal, Achmad and Dewanta, Favian and Prasasti, Anggunmeka Luhur and Ziani, Said},
title = {Comparative Deep Learning Models for Indonesian Gold Price Forecasting},
journal = {Advance Sustainable Science Engineering and Technology},
year = {2026},
volume = {8},
number = {3},
pages = {0260301},
doi = {10.26877/asset.v8i3.2608}
}
EUVIMED