A Hybrid Ensemble Deep Learning and Reservoir Computing Approach for Exchange Rate Prediction
DOI:
https://doi.org/10.4108/eettti.10443Keywords:
Exchange rate forecasting, Reservoir computing, Echo state networks, Time seriesAbstract
A nation's currency plays a vital role in stabilizing the economy and determining exchange rates in global markets. Keeping track of the influential currencies while comparing them with one's own currency becomes essential these days. During this study, we have specifically focused on the exchange rate prediction between the United States dollar (USD) and the Canadian dollar (CAD). This pair is one of the most active currency pairs with significant economic implications for both nations. This paper studies the use of machine learning models for this specific matter, which includes long short-term memory (LSTM), gated recurrent units (GRU), and reservoir computing (RC) echo state network models. They were evaluated not only as individual models but also in various hybrid combinations. A hybrid model which combines LSTM and RC yielded better performance in terms of Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Coefficient of Determination (R2). Moreover, the full potential of RC represents a promising direction for future researchers to incorporate into time series analysis. In addition, considering internal and external factors that influence the exchange rate during model development would also give more accurate predictions.
References
[1] Zsolt Darvas and Zoltán Schepp. Exchange rates and fundamentals: Forecasting with long maturity forward rates. Journal of International Money and Finance, 143: 103067, 2024. doi:10.1016/j.jimonfin.2024.103067. URL https://doi.org/10.1016/j.jimonfin.2024.103067. [Online; accessed 2024-05-01].
[2] Swagat Ranjit, Shruti Shrestha, Sital Subedi, and Subarna Shakya. Comparison of algorithms in foreign exchange rate prediction. In 2018 IEEE 3rd International Conference on Computing, Communication and Security (ICCCS). IEEE, 2018. Accessed: 2025-05-01.
[3] Blueberry Markets. What Are the Factors Affecting USD/CAD?, 2024. URL https://blueberrymarkets.com/market-analysis/what-are-the-factors-affecting-usdcad/. [Online; accessed 2025-05-01].
[4] Henri Makika, João Marcos Travassos Romano, and Rosângela Ballini. Deep learning techniques for time series forecasting: An application for exchange
rates. In 2023 IEEE International Workshop on Machine Learning for Signal Processing (MLSP). IEEE, 2023. doi:10.1109/MLSP55844.2023.10285930. URL https://doi.org/10.1109/MLSP55844.2023.10285930. [Online; accessed 2025-05-05].
[5] M.S. Islam and E. Hossain. Foreign exchange currency rate prediction using a gru-lstm hybrid network. Soft Computing Letters, 3:100009, 2021. doi:10.1016/j.socl.2020.100009. Accessed: 2025-05-01.
[6] Min Qi and Yangru Wu. Nonlinear prediction of exchange rates with monetary fundamentals. Journal of Empirical Finance, 10:623–640, 2003. doi:10.1016/S0927-5398(03)00008-2. URL https://www.elsevier.com/locate/econbase.
[7] Changqing Cheng, Akkarapol Sa-Ngasoongsong, Omer Beyca, Trung Le, Hui Yang, Zhenyu (James) Kong, and Satish T.S. Bukkapatnam. Time series forecasting for nonlinear and non-stationary processes: A review and comparative study. IIE Transactions, 47(10):1053–1071, 2015. doi:10.1080/0740817X.2014.999180. URL https: //doi.org/10.1080/0740817X.2014.999180. [Online; accessed 2024-05-01].
[8] Emilio Colombo and Matteo Pelagatti. Statistical learning and exchange rate forecasting. International Journal of Forecasting, 36(4):1260–1289, 2020.
doi:10.1016/j.ijforecast.2019.12.007. URL https://doi.org/10.1016/j.ijforecast.2019.12.007. [Online; accessed 2024-05-05].
[9] Bank of Canada. In Focus 2: Recent Factors Affecting the Canada–US Exchange Rate, 2025. URL https://www.bankofcanada.ca/publications/mpr/mpr-2025-01-29/in-focus-2/. [Online; accessed 2025-05-01].
[10] Investopedia. Loonie: Meaning, Overview, Role in Economy, 2022. URL https://www.investopedia.com/terms/l/loonie.asp. [Online; accessed 2025-05-01].
[11] Ranjan Dev, Md. Nur Alam, and Md. Lutfar Rahman. Arima model based time series modelling and prediction of foreign exchange rate against us dollar. International Journal of Recent Technology and Engineering, 11(3): 100–106, 2022. doi:10.35940/ijrte.C5792.111322. URL https://doi.org/10.35940/ijrte.C5792.111322. [Online; accessed 2025-05-05].
[12] Armin Lawi, Hendra Mesra, and Supri Amir. Imple- mentation of long short-term memory and gated recurrent units on grouped time-series data to predict stock prices accurately. Journal of Big Data, 9, 07 2022. doi:10.1186/s40537-022-00597-0.
[13] Herbert Jaeger. The "echo state" approach to analysing and training recurrent neural networks. GMD Report 148, German National Research Center for Information Technology, 2001.
[14] Wei-Jia Wang, Yong Tang, Jason Xiong, and Yi-Cheng Zhang. Stock market index prediction based on reservoir computing models. Expert Systems with Applications, 178:115022, 2021. ISSN 0957-4174. doi:10.1016/j.eswa.2021.115022. URL https://www.sciencedirect.com/science/article/pii/S0957417421004632.
[15] Ruobin Gao, Liang Du, Okan Duru, and Kum Fai Yuen. Time series forecasting based on echo state network and empirical wavelet transformation. Applied Soft Computing, 102:107111, 2021. doi:10.1016/j.asoc.2021.107111. URL https://doi.org/10.1016/j.asoc.2021.107111. Accessed: 2025-05-05.
[16] Linkon Barua and Mohammed Jamal Uddin. Exchange rate forecasting via generative adversarial network (gan). In 2024 IEEE International Conference on Computing, Applications and Systems (COMPAS). IEEE, 2024. doi:10.1109/COMPAS60761.2024.10796492. URL https://ieeexplore.ieee.org/document/10796492. [Online; accessed 2025-05-05].
[17] Google Finance. Google Finance, 2025. URL https://www.google.com/finance/. [Online; accessed 2025-03-14].
[18] Google Support. GOOGLEFINANCE function, 2025. URL https://support.google.com/docs/answer/3093281?hl=en. [Online; accessed 2025-03-14].
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Senthan Prasanth, Chau Phung
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
