Developing an LSTM-Based Forecasting Framework for Predicting Daily EUR/USD Price Direction in the Foreign Exchange Market
Article Sidebar
Main Article Content
Abstract
The foreign exchange (Forex) market is one of the largest and most liquid financial markets in the world. Predicting exchange-rate direction remains challenging because financial time-series data are highly volatile, nonlinear, and non-stationary. This study develops an LSTM-based forecasting framework for predicting the daily price direction of the EUR/USD exchange rate. The dataset consists of daily exchange-rate data exported from the MetaTrader 4 platform from 2 January 2018 to 30 April 2019, comprising 345 observations. The prediction task is formulated as a binary classification problem through a Trend variable, and sequential samples are generated using a sliding window technique for model training. The proposed framework investigates the effects of key parameters, including input window length, training data size, and model update frequency. In addition to the baseline LSTM model, optimized models and a classification-based sequence segmentation approach based on price movement characteristics (LSTM-CS) are developed to enable the model to learn different market patterns. The experimental results show that the baseline model achieved an accuracy of 52.5%, which increased to 67.5% after parameter optimization, while the LSTM-CS model produced the best result at 69.7%.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
The content and information in the articles published in the Journal of Science and Technology, Sisaket Rajabhat University reflect the opinions and responsibilities of the respective authors. The editorial board of the journal does not necessarily agree with, nor share responsibility for, these views.
Articles, information, content, images, etc., published in the Journal of Science and Technology, Sisaket Rajabhat University are copyrighted by the Faculty of Science and Technology, Sisaket Rajabhat University. If any individual or organization wishes to republish all or part of the content, or use it for any other purpose, they must obtain written permission from the Journal of Science and Technology, Sisaket Rajabhat University beforehand.
References
Aldridge, I. (2013). High-frequency trading: a practical guide to algorithmic strategies and trading systems. John Wiley & Sons.
Atsalakis, G. S., & Valavanis, K. P. (2009). Surveying stock market forecasting techniques–Part II: Soft computing methods. Expert Systems with applications, 36(3), 5932-5941. https://doi.org/10.1016/j.eswa.2008.07.006
Bank for International Settlements. (2022). OTC foreign exchange turnover in April 2022. Triennial Central Bank Survey. Retrieved December 12, 2025, from https://www.bis.org/statistics/rpfx22_fx.htm
Blaskowitz, O., & Herwartz, H. (2011). On economic evaluation of directional forecasts. International Journal of Forecasting, 27(4), 1058–1065. https://doi.org/10.1016/j.ijforecast.2010.09.003
Brownlee, J. (2018). Deep learning for time series forecasting: Predict the future with MLPs, CNNs and LSTMs in Python. Machine Learning Mastery. Retrieved December 12, 2025, from https://machinelearningmastery.com/deep-learning-for-time-series-forecasting/
Cao, L. J., Tay, F. E. H., & Liu, J. (2003). Support vector machines with adaptive parameters in financial time series forecasting. IEEE Transactions on Neural Networks, 14(6), 1506–1518. https://doi.org/10.1109/TNN.2003.820556
Evans, M. D. D., & Lyons, R. K. (2002). Order flow and exchange rate dynamics. Journal of Political Economy, 110(1), 170–180. https://doi.org/10.1086/324391
Fischer, T., & Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research, 270(2), 654–669. https://doi.org/10.1016/j.ejor.2017.11.054
García, F., Guijarro, F., Oliver, J., & Tamošiūnienė, R. (2024). Foreign exchange forecasting models: LSTM and BiLSTM comparison. Engineering Proceedings, 68(1), Article 19. https://doi.org/10.3390/engproc2024068019
Gu, S., Kelly, B., & Xiu, D. (2020). Empirical asset pricing via machine learning. The Review of Financial Studies, 33(5), 2223–2273. https://doi.org/10.1093/rfs/hhaa009
Guyard, K. C., & Deriaz, M. (2024, August). Predicting foreign exchange EUR/USD direction using machine learning. In Proceedings of the 2024 7th International Conference on Machine Learning and Machine Intelligence (MLMI) (pp. 1-9). https://doi.org/10.1145/3696271.3696272
Hochreiter, S. (1998). The vanishing gradient problem during learning recurrent neural networks. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 6(2), 107–116. https://doi.org/10.1142/S0218488598000094
Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
Kamruzzaman, J., & Sarker, R. A. (2003). Comparing ANN based models with ARIMA for prediction of forex rates. ASOR Bulletin, 22(2), 2–11.
King, M. R., Osler, C., & Rime, D. (2013). The market microstructure approach to foreign exchange: Looking back and looking forward. Journal of Economic Literature, 51(4), 1090–1134. https://doi.org/10.1257/jel.51.4.1090
Lim, B., & Zohren, S. (2021). Time-series forecasting with deep learning: A survey. Philosophical Transactions of the Royal Society A, 379(2194), Article 20200209. https://doi.org/10.1098/rsta.2020.0209
Lo, A. W., Mamaysky, H., & Wang, J. (2000). Foundations of technical analysis: Computational algorithms, statistical inference, and empirical implementation. The Journal of Finance, 55(4), 1705–1765. https://doi.org/10.1111/0022-1082.00265
Lyons, R. K. (2001). The microstructure approach to exchange rates. the MIT Press.
Moosa, I. A. (2015). On the evaluation of directional forecasts. Applied Economics, 47(57), 6191–6199. https://doi.org/10.1080/00036846.2015.1064086
Nguyen, P. D., Thao, N. N., Chi, D. T. K., Nguyen, H. C., Mach, B. N., & Nguyen, T. Q. (2024). Deep learning-based predictive models for forex market trends: Practical implementation and performance evaluation. Science Progress, 107(3), 00368504241275370. https://doi.org/10.1177/00368504241275370
Pascanu, R., Mikolov, T., & Bengio, Y. (2013). On the difficulty of training recurrent neural networks. Neural Networks, 37, 1–11. https://doi.org/10.1016/j.neunet.2012.02.010
Poon, S. H., & Granger, C. W. J. (2003). Forecasting volatility in financial markets: A review. Journal of Economic Literature, 41(2), 478–539. https://doi.org/10.1257/002205103765762743
Rapach, D., & Zhou, G. (2013). Forecasting stock returns. In Handbook of economic forecasting (Vol. 2, pp. 328-383). Elsevier.
Sezer, O. B., Gudelek, M. U., & Ozbayoglu, A. M. (2020). Financial time series forecasting with deep learning: A systematic literature review: 2005–2019. Applied Soft Computing, 90, 106181. https://doi.org/10.1016/j.asoc.2020.106181
Tharp, V. K., Chabot, C., & Tharp, K. (2007). Trade your way to financial freedom (p. 343). New York, NY, USA: McGraw-Hill.
Vince, R. (1992). The mathematics of money management: risk analysis techniques for traders. John Wiley & Sons.
Zhang, Z., Zohren, S., & Roberts, S. (2022). Deep learning for volatility forecasting. Quantitative Finance, 22(2), 357–372. https://doi.org/10.1080/14697688.2021.1989139
