EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Comparative Analysis of Statistical, Machine Learning, and Deep Learning Models for USD/IDR Prediction Using Macroeconomic Indicators and Explainable Artificial Intelligence

Deva Putra Setyawan, Astrid Sulistya Azahra, Mugi Lestari, Moch Panji Agung Saputra

International Journal of Mathematics, Statistics, and Computing · 07.08.2026 · 4 (3) · 170-188

DOI: 10.46336/ijmsc.v4i3.351 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Mathematics, Statistics, and Computing, online erschienen am 07.08.2026. Verfasst von Deva Putra Setyawan und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The USD/IDR exchange rate is a key daily barometer of Indonesia's economic health. Accurate forecasting is vital for trade, inflation, and monetary stability. However, its volatile and nonlinear dynamics pose challenges. While research has applied statistical models, machine learning, and deep learning, few studies offer a comprehensive comparison integrating predictive accuracy with model interpretability, particularly using banking stock prices as exogenous predictors. This study addresses this gap by developing and evaluating eight forecasting approaches—a naive random-walk baseline, two statistical models (ARIMA, SARIMAX), three tree-based ensembles (Random Forest, XGBoost, LightGBM), and two recurrent neural networks (LSTM, GRU) using daily data from January 2015 to July 2026 (3,005 observations). Five major banking stocks (BBCA, BBRI, BMRI, BBNI, BDMN) are included as one-day-lagged exogenous features. Models are assessed via hold-out testing and five-fold walk-forward cross-validation using RMSE, MAE, MAPE, and R². Contrary to expectations, the naive random-walk consistently achieves the lowest error (RMSE=115.24, MAE=63.80, MAPE=0.39%) and the most stable performance, with LSTM as the best-performing complex model (RMSE=269.59, R²=0.785). Diebold-Mariano tests confirm statistical significance (p

Zitieren

APA

Setyawan, D. P., Azahra, A. S., Lestari, M., & Saputra, M. P. A. (2026). Comparative Analysis of Statistical, Machine Learning, and Deep Learning Models for USD/IDR Prediction Using Macroeconomic Indicators and Explainable Artificial Intelligence. International Journal of Mathematics, Statistics, and Computing, 4(3), 170-188. https://doi.org/10.46336/ijmsc.v4i3.351

Vancouver

Setyawan DP, Azahra AS, Lestari M, Saputra MPA. Comparative Analysis of Statistical, Machine Learning, and Deep Learning Models for USD/IDR Prediction Using Macroeconomic Indicators and Explainable Artificial Intelligence. International Journal of Mathematics, Statistics, and Computing. 2026;4(3):170-188. doi:10.46336/ijmsc.v4i3.351

BibTeX
@article{Setyawan2026,
  author = {Setyawan, Deva Putra and Azahra, Astrid Sulistya and Lestari, Mugi and Saputra, Moch Panji Agung},
  title = {Comparative Analysis of Statistical, Machine Learning, and Deep Learning Models for USD/IDR Prediction Using Macroeconomic Indicators and Explainable Artificial Intelligence},
  journal = {International Journal of Mathematics, Statistics, and Computing},
  year = {2026},
  volume = {4},
  number = {3},
  pages = {170--188},
  doi = {10.46336/ijmsc.v4i3.351}
}
Kostenlos starten →