Integrating Economic Indicators and Machine Learning for Exchange Rate Forecasting
DOI:
https://doi.org/10.70862/CSIR.2025.0202-16Keywords:
Ensemble Machine Learning Methods, Macroeconomic Indicators, Exchange Rate ForecastingAbstract
This study presents an integrated framework for forecasting the USD/JPY exchange rate using ensemble machine learning techniques – CART-Ensembles and Arcing. The analysis employs monthly macroeconomic data from October 1987 to April 2025. Key predictive variables include differentials in interest rates, inflation, unemployment, and government bond yields between the United States and Japan. After a preliminary time-series analysis and feature selection, ensemble models were developed for four distinct time periods. Each model performs step-by-step forecasts up to four months ahead (January–April 2025), achieving exceptionally high predictive accuracy, with coefficients of determination (R²) above 0.98 and mean absolute percentage errors (MAPE) below 1%. The results demonstrate that combining macroeconomic fundamentals with advanced ensemble learning methods significantly enhances the accuracy, robustness, and reliability of exchange rate forecasting. These findings provide policymakers and investors with a robust analytical tool for anticipating short-term currency fluctuations under varying macroeconomic conditions.
References
Byrne, J. P., Korobilis, D., & Ribeiro, P. J. (2016). Exchange rate predictability in a changing world. Journal of International Money and Finance, 62, 1–24. https://doi.org/10.1016/j.jimonfin.2015.12.001
Mishkin, F. S. (2012). Economics of money, banking, and financial markets (10th ed.). Prentice Hall.
Parkin, M. (2011). Economics (10th ed.). Prentice Hall.
Elliott, G., & Timmermann, A. (Eds.). (2013). Handbook of economic forecasting (Vol. 2). North Holland.
Fabozzi, F. J., & Mann, S. V. (2012). The handbook of fixed income securities. McGraw-Hill Education.
Tripathi, M., Kumar, S., & Inani, S. K. (2021). Exchange rate forecasting using ensemble modeling for better policy implications. Journal of Time Series Econometrics, 13(1), 43–71. https://doi.org/10.1515/jtse-2020-0013
Tsuji, C. (2022). Exchange rate forecasting via a machine learning approach. iBusiness, 14(3). https://doi.org/10.4236/ib.2022.143009
Khashei, M., Rafiei, F. M., & Bijari, M. (2013). Hybrid fuzzy auto-regressive integrated moving average (FARIMAH) model for forecasting the foreign exchange markets. International Journal of Computational Intelligence Systems, 6, 954–968. https://doi.org/10.1080/18756891.2013.809937
El Mahjouby, M., Taj Bennani, M., Lamrini, M., Bossoufi, B., Alghamdi, T. A. H., & El Far, M. (2024). Machine learning algorithms for forecasting and categorizing euro-to-dollar exchange rates. IEEE Access, 12, 74211–74217. https://doi.org/10.1109/ACCESS.2024.3404824
Sun, S., Wang, S., & Wei, Y. (2020). A new ensemble deep learning approach for exchange rates forecasting and trading. Advanced Engineering Informatics, 46, 101160. https://doi.org/10.1016/j.aei.2020.101160
Theofilatos, K., Likothanassis, S., & Karathanasopoulos, A. (2012). Modeling and trading the EUR/USD exchange rate using machine learning techniques. Engineering, Technology & Applied Science Research, 2(5), 269–272. https://doi.org/10.48084/etasr.200
Guyard, K. C., & Deriaz, M. (2024). Predicting foreign exchange EUR/USD direction using machine learning. In Proceedings of the 2024 7th International Conference on Machine Learning and Machine Intelligence (MLMI '24) (pp. 1–9). Association for Computing Machinery. https://doi.org/10.1145/3696271.3696272
Wang, G., Tao, T., Ma, J., Li, H., Fu, H., & Chu, Y. (2021). An improved ensemble learning method for exchange rate forecasting based on the complementary effect of shallow and deep features. Expert Systems with Applications, 184, 115569. https://doi.org/10.1016/j.eswa.2021.115569
Zhou, Z.-H. (2012). Ensemble methods: Foundations and algorithms. CRC Press. https://doi.org/10.1201/b12207
Opitz, D., & Maclin, R. (1999). Popular ensemble methods: An empirical study. Journal of Artificial Intelligence Research, 11, 169–198. https://doi.org/10.1613/jair.614
Breiman, L. (1998). Arcing classifiers. The Annals of Statistics, 26(3), 801–849. https://doi.org/10.1214/aos/1024691079
Obstfeld, M., & Rogoff, K. (1996). Foundations of international macroeconomics. MIT Press.
Taylor, A. M., & Taylor, M. P. (2004). The purchasing power parity debate. Journal of Economic Perspectives, 18(4), 135–158. https://doi.org/10.1257/0895330042632744
Engel, C., & West, K. D. (2005). Exchange rates and fundamentals. Journal of Political Economy, 113(3), 485–517. https://doi.org/10.1086/429137
Bernoth, K., & Erdogan, B. (2012). Sovereign bond yield spreads: A time-varying coefficient approach. Journal of International Money and Finance, 31(3), 639–656. https://doi.org/10.1016/j.jimonfin.2011.10.006
Downloads
Published
Issue
Section
Categories
License
Copyright (c) 2025 Ivaylo Boyoukliev , Vanya Ivanova , Hristina Kulina, Boyan Zlatanov (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
