📅 24 May 2026
DOI: 10.26877/asset.v8i3.2608
Comparative Deep Learning Models for Indonesian Gold Price Forecasting
Advance Sustainable Science, Engineering and Technology (ASSET)
Universitas Persatuan Guru Republik Indonesia Semarang
📄 Abstract
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.
🔖 Keywords
#Bayesian optimization; deep learning; gold price forecasting; LSTM-GRU; time-series prediction
ℹ️ Informasi Publikasi
Tanggal Publikasi
24 May 2026
Volume / Nomor / Tahun
Tahun 2026
📝 HOW TO CITE
Putra, Albi Pernata Jomantara; Williamsyah, Baginda Mi’raj; Rizal, Achmad; Dewanta, Favian ; Prasasti, Anggunmeka Luhur ; Ziani, Said, "Comparative Deep Learning Models for Indonesian Gold Price Forecasting," Advance Sustainable Science, Engineering and Technology (ASSET), May. 2026.
ACM
ACS
APA
ABNT
Chicago
Harvard
IEEE
MLA
Turabian
Vancouver
Download Citation
0
Sitasi
Cek Google Scholar