Machine learning for exchange rate forecasting: a case study on SAR/PKR, SAR/IDR, and USD/IDR
Acta Logistica · 30.06.2026 · 13 (2) · 431
DOI: 10.22306/al.v13i2.785 ↗Kurz gefasst
Fachartikel in der Zeitschrift Acta Logistica, online erschienen am 30.06.2026. Verfasst von Yarham Syahabi Lubis und 4 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben.
Abstract (Originalsprache)
Exchange rate prediction is essential in industries such as travel, finance, and religious tourism, particularly to Indonesia and Pakistan as the sources of Umrah and Hajj pilgrims to Saudi Arabia. This paper compares machine learning models, namely, Long Short-Term Memory (LSTM), Support Vector Regression (SVR), and Multi-layer Perceptron (MLP), in predicting SAR/PKR, SAR/IDR, and USD/IDR rates based on historical data. While prior research noted LSTM's utility during periods like the COVID-19 pandemic, its precision remained limited. This work evaluates models using key metrics: Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared.Results identify LSTM as the most effective for the SAR/PKR pair, achieving an MSE of 26.814, RMSE of 5.178, MAE of 3.370, and R-squared of 0.8685. However, for the SAR/IDR and USD/IDR pairs, the SVR model demonstrated superior performance with lower errors. For SAR/IDR, it recorded an MSE of 768.295, RMSE of 27.718, MAE of 20.788, and R-squared of 0.9768. For USD/IDR, metrics were an MSE of 17752.818, RMSE of 133.239, MAE of 108.761, and R-squared of 0.9631.The findings validate SVR's reliability for forecasting these specific currency pairs. This analysis provides valuable insights for travelers, investors, and pilgrimage stakeholders, enabling better currency risk management in religious tourism and related financial activities.
Zitieren
APA
Lubis, Y. S., Basingab, M., Mirdad, W., Alahmadi, M., & Dermawan, A. A. (2026). Machine learning for exchange rate forecasting: a case study on SAR/PKR, SAR/IDR, and USD/IDR. Acta Logistica, 13(2), 431. https://doi.org/10.22306/al.v13i2.785
Vancouver
Lubis YS, Basingab M, Mirdad W, Alahmadi M, Dermawan AA. Machine learning for exchange rate forecasting: a case study on SAR/PKR, SAR/IDR, and USD/IDR. Acta Logistica. 2026;13(2):431. doi:10.22306/al.v13i2.785
BibTeX
@article{Lubis2026,
author = {Lubis, Yarham Syahabi and Basingab, Mohammed and Mirdad, Waleed and Alahmadi, Mazin and Dermawan, Aulia Agung},
title = {Machine learning for exchange rate forecasting: a case study on SAR/PKR, SAR/IDR, and USD/IDR},
journal = {Acta Logistica},
year = {2026},
volume = {13},
number = {2},
pages = {431},
doi = {10.22306/al.v13i2.785}
}
EUVIMED