Exchange Rate Prediction Under Data Volatility: A Comparison Of Deep Learning Techniques

Filiz Erataş Sönmez; Şule Öztürk Birim

doi:10.57019/jmv.1841380

Exchange Rate Prediction Under Data Volatility: A Comparison Of Deep Learning Techniques

Abstract

This Accurate prediction of exchange rates is of critical importance for economic policy related decision making. This study employs a deep learning based framework to model exchange rate dynamics by explicitly accounting for the inherently nonlinear, and regime sensitive nature of financial time series. Unlike traditional artificial neural network approaches that overlook temporal dependencies, recurrent neural network architectures are capable of directly modeling long term time dependencies. Accordingly, this study applies Long Short Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM), and Gated Recurrent Unit (GRU) models to predict the USD/TRY and EUR/TRY exchange rate series. The empirical analysis is conducted using data from the Turkish economy across three distinct subperiods, representing a relatively stable regime and two high-volatility regimes. Hyperparameters are independently optimized for each model and regime with grid search. Predictive performance is evaluated using Mean Absolute Error, Root Mean Squared Error, and Mean Absolute Percentage Error, with Diebold Mariano tests confirming statistical significance and formal benchmark comparisons against ARIMA and random walk models. Results indicate that no single architecture dominates across all conditions: GRU consistently outperforms competitors during the Crisis period for both exchange rates, while LSTM and BiLSTM perform best during COVID19 for USD/TRY, and GRU maintains its advantage for EUR/TRY. Diebold Mariano tests confirm that 89% of pairwise performance differences are statistically significant. Robustness analysis using lag-3 specifications supports that regime-dependent patterns are not artifacts of input structure. By incorporating volatility regimes, statistical testing, and econometric benchmarks, this study demonstrates the practical importance of regime-aware model selection for exchange rate forecasting in emerging market economies.

Keywords

Supporting Institution

This research did not receive any outside funding or support. The authors report no involvement in the research by the sponsor that could have influenced the outcome of this work.

Ethical Statement

In this article, the principles of scientific research and publication ethics were followed. This study did not involve human or animal subjects and did not require additional ethics committee approval.

References

Abedin, M. Z., Moon, M., Hassan, M., & Ha´jek, P. (2021). Deep learning-based exchange rate prediction during the COVID-19 pandemic. Annals of Operations Research, 1–52. https://doi.org/10.1007/s10479-021-04420-6
Adam, K., Smagulova, K. and James, A. P. (2018). Memristive LSTM network hardware architecture for time series predictive modeling problems. arXiv preprint arxiv:1809.03119v1. https://doi.org/10.48550/arXiv.1809.03119
Altan, S¸. (2008). Doviz kuru ongoru performansı için alternatif bir yaklaşım: yapay sinir ağı. Journal of Gazi University Faculty of Economics and Administrative Sciences, 10(2), 141–160. https://izlik.org/JA87WB59FC
Ang, A., & Bekaert, G. (2002). Regime switches in interest rates. Journal of Business & Economic Statistics, 20(2), 163-182. https://doi.org/10.1198/073500102317351930
Ayoobi, N., Sharifrazi, D., Alizadehsani, R., Shoeibi, A., Gorriz, J.M., Moosaei, H., Khosravi, A., Nahavandi, S., Gholamzadeh Chofreh, A., Goni, F.A., Klemeˇs, J.J. & Mosavi, A., (2021). Time series forecasting of new cases and new deaths rate for COVID-19 using deep learning methods. The results in Physics, 27, 104495. https://doi.org/10.1016/j.rinp.2021.104495
Azzouni, A. & Pujolle, G. (2017). A Long short-term memory recurrent neural network framework for network traffic matrix prediction. arxiv preprint arxiv:1705.05690v2. https://doi.org/10.48550/arXiv.1705.05690
Bahdanau, D., Cho, K., & Bengio, Y. (2015). Neural machine translation by jointly learning to align and translate. International Conference on Learning Representations (ICLR 2015). https://arxiv.org/abs/1409.0473
Bian, G., McAleer, M., & Wong, W. K. (2013). Robust estimation and forecasting of the capital asset pricing model. Annals of Financial Economics, 8(02), 1350007. https://doi.org/10.1142/S2010495213500073

Borovkova, S. & I. Tsiamas (2019). An ensemble of LSTM neural networks for high-frequency stock market classification. Journal of Forecasting, 38, 600-618. https://doi.org/10.1002/for.2585
Bui, T. C., Le, V. D. & Cha, S. K. (2018). A deep learning approach for forecasting air pollution in south korea using LSTM. arxiv preprint arxiv:1804.07891. https://doi.org/10.48550/arXiv.1804.07891
Cheung, Y. W., Chinn, M. D., & Pascual, A. G. (2005). Empirical exchange rate models of the nineties: are any fit to survive?. Journal of International Money and Finance, 24(7), 1150–1175. https://doi.org/10.1016/j.jimonfin.2005.08.002
Cho, K., Merrienboer, B, Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H. & Yoshua Be. (2014). Learning phrase representations using RNN encoder–decoder. EMNLP, 1724–1734. https://doi.org/10.48550/arXiv.1406.1078
Chung, J., Gulcehre, C., Cho, K & Bengio, Y, (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555. https://doi.org/10.48550/arXiv.1412.3555
Clements, K. W. & Lan, Y., (2010). A new approach to forecasting exchange rates. Journal of International Money and Finance, 29(7), 1424-1437. https://doi.org/10.1016/j.jimonfin.2010.03.009
Coats, P., L. Fant, (1993). Recognizing financial distress patterns using a neural network tool. Financial Management, 22(3), 142-155. https://www.jstor.org/stable/3665934
Datta, R.K., Sajid, S.W. & Moon, M.H. (2021). Foreign currency exchange rate prediction using bidirectional long short term memory. In: Al-Sartawi, A.M.A.M. (Ed.), The Big Data-Driven digital economy: artificial and computational intelligence. Springer, pp. 213–227. https://doi.org/10.1007/978-3-030-73057-4_17
Dautel, A.J., Ha¨rdle, W.K., Lessmann, S. & Seow, H.-V. (2020). Forex exchange rate predicting using deep recurrent neural networks. Digital Finance, 2, 69–96. https://doi.org/10.1007/s42521-020-00019-x
Demirci, E. & Karaatli, M. (2023). Kripto para fiyatlarının LSTM ve GRU Modelleri ile tahmini. Journal of Mehmet Akif Ersoy University Economics and Administrative Sciences Faculty, 10(1), 134-157. https://doi.org/10.30798/makuiibf.1035314
Diebold, F. X. & Mariano. R. S. (1995). Comparing predictive accuracy. Journal of Business & Economic Statistics, 13(3), 253-263. https://doi.org/10.2307/1392185
Dutta, A., Kumar, S. & M. Basu (2020). A gated recurrent unit approach to bitcoin price prediction. Journal of Risk and Financial Management, 13(2), 23. 1-16. https://doi.org/10.3390/jrfm13020023
Elliott, G., & Timmermann, A. (2008). Economic forecasting. Journal of Economic Literature, 46(1), 3–56. https://doi.org/10.1257/jel.46.1.3
Engel, C., & West, K. D. (2005). Exchange rates and fundamentals. Journal of Political Economy, 113(3), 485–517. https://doi.org/10.1086/429137
Engle, R. F., & Bollerslev, T. (1986). Modelling the persistence of conditional variances. Econometric Reviews, 5(1), 1-50. https://doi.org/10.1080/07474938608800095
Feng, H. & Shu, Y. (2005). Study on network traffic prediction techniques. proceedings. 2005 International Conference on Wireless Communications, Networking and Mobile Computing, 2005., 2(3), 995–998. https://doi.org/10.1109/WCNM.2005.1544219
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
Franses, P. H. (2020). Simple bayesian forecast combination. Annals of Financial Economics, 15(04), 2050016. https://doi.org/10.1142/S2010495220500165
Garcia-Medina, A., & Aguayo-Moreno, E. (2024). LSTM–GARCH hybrid model for the prediction of volatility in cryptocurrency portfolios. Computational Economics, 63(4), 1511-1542. https://doi.org/10.1007/s10614-023-10373-8
Gers, F. A., & Schmidhuber, E. (2001). LSTM recurrent networks learn simple context-free and context-sensitive languages. IEEE Transactions On Neural Networks, 12(6), 1333-1340. https://doi.org/10.1109/72.963769
Gonçalves, R., Ribeiro, V. M., Pereira, F. L., & Rocha, A. P. (2019). Deep learning in exchange markets. Information Economics and Policy, 47, 38-51. https://doi.org/10.1016/j.infoecopol.2019.05.002
Graves, A., & Schmidhuber, J. (2005). Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Networks, 18(5–6), 602–610. https://doi.org/10.1016/j.neunet.2005.06.042
Gray, S. F. (1996). Modeling the conditional distribution of interest rates as a regime-switching process. Journal of Financial Economics, 42(1), 27-62. https://doi.org/10.1016/0304-405X(96)00875-6
Guidolin, M., & Timmermann, A. (2008). International asset allocation under regime switching, skew, and kurtosis preferences. The Review of Financial Studies, 21(2), 889-935. https://doi.org/10.1093/rfs/hhn006
Gupta, R., Pierdzioch, C., & Wong, W. K. (2021). A note on forecasting the historical realized variance of oil price movements: the role of gold-to-silver and gold-to-platinum price ratios. Energies, 14(20), 6775, 1-12. https://doi.org/10.3390/en14206775
Haefke, C. & Helmenstein, C. (1996). Forecasting Austrian IPOs: An Application of Linear and Neural Network Error-Correction Models. Journal of Forecasting, 15(3), 237-251. https://doi.org/10.1002/(SICI)1099-131X(199604)15:3<237::AID-FOR621>3.0.CO;2-5
Hamayel, M.J. & Owda, A.Y. (2021) A novel cryptocurrency price prediction model using gru, lstm and bi-lstm machine learning algorithms. AI, 2(4), 477–496. https://doi.org/10.3390/ai2040030
Hamilton, J. D., & Susmel, R. (1994). Autoregressive conditional heteroskedasticity and changes in regime. Journal of Econometrics, 64(1-2), 307-333. https://doi.org/10.1016/0304-4076(94)90067-1
Hann, T. H., & Steurer, E. (1996). Much ado about nothing? exchange rate forecasting: neural networks vs. linear models using monthly and weekly data. Neurocomputing, 10(4), 323-339. https://doi.org/10.1016/0925-2312(95)00137-9
Hornik, K., Stinchcombe, M., & White, H. (1989). Multilayer feedforward networks are universal approximators. Neural networks, 2(5), 359-366. https://doi.org/10.1016/0893-6080(89)90020-8
Hossain, M. F. B., Lamia, L. Z., Rahman, M. M., & Khan, M. M. (2024). finbertbilstm: a deep learning model for predicting volatile cryptocurrency market prices using market sentiment dynamics. arXiv preprint arXiv:2411.12748. https://doi.org/10.48550/arXiv.2411.12748
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
Huang, J., Chai, J., & Cho, S. (2020). Deep learning in finance and banking: A literature review and classification. Frontiers of Business Research in China, 14(1), 13, 1-24. https://doi.org/10.1186/s11782-020-00082-6
Jing, J., Yan, W., & Deng, X. (2021). A hybrid model to estimate corporate default probabilities in China based on zero-price probability model and long short-term memory. Applied Economics Letters, 28(5), 413–420. https://doi.org/10.1080/13504851.2020.1757611
Kamruzzaman, J. & R. A. Sarker (2003). Forecasting of Currency Exchange Rates Using ANN: A Case Study. International Conference on Neural Networks and Signal Processing, Proceedings of the 2003, 793-797. https://doi.org/10.1109/ICNNSP.2003.1279395
Kazakov, O. D., & Mikheenko, O. V. (2020). Transfer learning and domain adaptation based on modeling of socioeconomic systems. Бизнес-информатика, 14(2), 7-20. https://doi.org/10.17323/2587-814X.2020.2.7.20
Khan, Z., Khan, S. M., Dey, K., & Chowdhury, M. (2019). Development and evaluation of recurrent neural network-based models for hourly traffic volume and annual average daily traffic prediction. Transportation Research Record, 2673(7), 489-503. https://doi.org/10.1177/0361198119849059
Kim, D., & Baek, C. (2020). Factoraugmented HAR model improves realized volatility forecasting. Applied Economics Letters, 27(12), 1002-1009. https://doi.org/10.1080/13504851.2019.1657554
Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. Proceedings of the 3rd International Conference on Learning Representations (ICLR 2015). https://doi.org/10.48550/arXiv.1412.6980
Klaassen, F. (2002). Improving GARCH volatility forecasts with regime-switching GARCH. Empirical Economics, 27(2), 363394. https://doi.org/10.1007/s001810100100
Kuan, C. M., & Liu, T. (1995). Forecasting exchange rates using feedforward and recurrent neural networks. Journal of applied econometrics, 10(4), 347-364. https://doi.org/10.1002/jae.3950100403
Moon, K. & Kim, H. (2019). Performance of deep learning in prediction of stock market volatility. Economic Computation & Economic Cybernetics Studies & Research, 53(2), 77-92. https://doi.org/10.24818/18423264/53.2.19.05
Lamoureux, C. G., & Lastrapes, W. D. (1990). Persistence in variance, structural change, and the GARCH model. Journal of Business & Economic Statistics, 8(2), 225-234. https://doi.org/10.2307/1391985
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444. https://doi.org/10.1038/nature14539
Lisi, F., & Schiavo, R. A. (1999). A comparison between neural networks and chaotic models for exchange rate prediction. Computational Statistics & Data Analysis, 30(1), 87-102. https://doi.org/10.1016/S0167-9473(98)00067-X
Meese, R. A., & Rogoff, K. (1983). Empirical exchange rate models of the seventies: Do they fit out of sample? Journal of International Economics, 14(1–2), 3–24. https://doi.org/10.1016/0022-1996(83)90017-X
Nakisa, B., Rastgoo, M. N., Rakotonirainy, A., Maire, F., & Chandran, V. (2018). Long short term memory hyperparameter optimization for a neural network based emotion recognition framework. IEEE Access, 6, 49325-49338. https://doi.org/10.1109/ACCESS.2018.2868361
Narowski, D., Santos, C., Borowski, L., Apollo, M., & Maciuk, K. (2025). Valuation and volatility of virtual properties in metaverse: exploring new market opportunities and speculative dynamics based on decentraland. Journal of Metaverse, 5(1), 1-24. https://doi.org/10.57019/jmv.1588762
Nelson, D. B. (1990). Stationarity and persistence in the GARCH(1,1) model. Econometric Theory, 6(3), 318-334. https://www.jstor.org/stable/3532198
Özkan,F. (2012). Döviz kuru tahmininde parasal model ve yapay sinir ağları karşılaştırması. Business and Economics Research Journal, 3(1), 27-39.
Panda, C., & Narasimhan, V. (2007). Forecasting exchange rate better with artificial neural network. Journal of Policy Modeling, 29(2), 227-236. https://doi.org/10.1016/j.jpolmod.2006.01.005
Park, D. & Ryu, D. (2021). Forecasting stock market dynamics using bidirectional long short-term memory. Romanian Journal of Economic Forecasting, 24(2), 22-34.
Pascanu, R., Mikolov, T., & Bengio, Y. (2013). On the difficulty of training recurrent neural networks. Proceedings of the 30th International Conference on Machine Learning (ICML 2013), 28, 1310–1318. https://doi.org/10.48550/arXiv.1211.5063
Pichl, L. & T. Kaizoji (2017). Volatility analysis of bitcoin price time series. Quantative Finance and Economics, 1(4), 474-485. https://doi.org/10.3934/QFE.2017.4.474
Ranjit, S., Shrestha, S., Subedi, S., & Shakya, S. (2018, October). Comparison of algorithms in foreign exchange rate prediction. In 2018 IEEE 3rd International Conference on Computing, Communication and Security (ICCCS) (pp. 9-13). IEEE. https://doi.org/10.1109/CCCS.2018.8586826
Rossi, B. (2013). Exchange rate predictability. Journal Of Economic Literature, 51(4), 10631119. https://doi.org/10.1257/jel.51.4.1063
Islam, M. S., & Hossain, E. (2021). Foreign exchange currency rate prediction using a GRU-LSTM hybrid network. Soft Computing Letters, 3, 100009, 1-17. https://doi.org/10.1016/j.socl.2020.100009
Sak, H., Senior, A., & Beaufays, F. (2014). Long short-term memory based recurrent neural network architectures for large vocabulary speech recognition. arXiv preprint arXiv:1402.1128v1. https://doi.org/10.48550/arXiv.1402.1128
Seabe, P. L., Moutsinga, C. R. B., & Pindza, E. (2023). Forecasting cryptocurrency prices using LSTM, GRU, and bidirectional LSTM: a deep learning approach. Fractal and Fractional, 7(2), 203, 1-18. https://doi.org/10.3390/fractalfract7020203
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
Schuster, M., & Paliwal, K. K. (1997). Bidirectional recurrent neural networks. IEEE transactions on Signal Processing, 45(11), 2673-2681. https://doi.org/10.1109/78.650093
Shahid, F., Zameer, A., & Muneeb, M. (2020). Predictions for COVID-19 with deep learning models of LSTM, GRU and Bi-LSTM. Chaos, Solitons & Fractals, 140, 110212. https://doi.org/10.1016/j.chaos.2020.110212
Siami-Namini, S., Tavakoli, N., & Namin, A. S. (2019). A comparison of ARIMA and LSTM in forecasting time series. Proceedings of the 2018 IEEE International Conference on Machine Learning and Applications (ICMLA), 1394–1401. https://doi.org/10.1109/ICMLA.2018.00227
Smyl, S. (2020). A hybrid method of exponential smoothing and recurrent neural networks for time series forecasting. International Journal of Forecasting, 36(1), 75-85. https://doi.org/10.1016/j.ijforecast.2019.03.017
Song, YP., Li, ZW., Ma, ZR., & Sun, XY. (2023). Dynamic forecasting for nonstationary high-frequency financial data with jumps based on series decomposition and reconstruction. Journal of Forecasting, 42(5), 10551068. https://doi.org/10.1002/for.2934Digital Object Identifier (DOI)
Soy Temür, A., Akgün, M., & Temür G. (2019). Predicting housing sales in Turkey using ARIMA, LSTM and hybrid models. Journal of Business Economics and Management (JBEM), 20(5), 920-938. https://doi.org/10.3846/jbem.2019.10190
Su, Z., Xie, H., & Han, L. (2021). Multi-factor RFG-LSTM algorithm for stock sequence predicting. Computational Economics, 57(4), 1041-1058. https://doi.org/10.1007/s10614-020-10008-2
Tas, O., Yakak, E., & Ugurlu, U. (2018). Using artificial neural network and a statistical method for the estimation of Euro/Turkish Lira exchange rate. Press Academia Procedia, 7-2018(79), 414-417. https://doi.org/10.17261/Pressacademia.2018.926
Turak, N., (2018, 14 August). Turkish lira recovers sharply against the dollar after record nosedive. CNBC. URL l https://www.cnbc.com/2018/08/14/turkish-lira-recovers-sharply-against-the-dollar-after-record-nosedive.html
Verlinden, B., Duflou, J. R., Collin, P., & Cattrysse, D. (2008). Cost estimation for sheet metal parts using multiple regression and artificial neural networks: A case study. International Journal of Production Economics, 111(2), 484-492. https://doi.org/10.1016/j.ijpe.2007.02.004
Weigend, A. (1992). Predicting sunspots and exchange rates with connectionist networks. Nonlinear Modelling And Forecasting, 395-431.
Yıldıran, C. U., & Fettahog˘lu, A. (2017). Forecasting USDTRY rate by ARIMA method. Cogent Economics & Finance, 5(1), 1335968. https://doi.org/10.1080/23322039.2017.1335968
Zengeler, N., & Handmann, U. (2020). Contracts For Difference: A Reinforcement Learning Approach. Journal of Risk and Financial Management, 13(4), 78, 1-12. https://doi.org/10.3390/jrfm13040078
Zhang, K., Hong, M., Zhang, K., & Hong, M. (2022). Forecasting crude oil price using LSTM neural networks. Data science in Finance and Economics, 2(3), 163-180. https://doi.org/10.3934/DSFE.2022008
Zhang, P.G., (2003). Time Series Forecasting Using a hybrid ARIMA and neural network model. Neurocomputing, 50, 159–175. https://doi.org/10.1016/S0925-2312(01)00702-0
Zouaoui, H., & Naas, M. N. (2023). Option pricing using deep learning approach based on LSTM-GRU neural networks: Case of London stock exchange. Data Science in Finance and Economics, 3(3), 267-284. https://doi.org/10.3934/DSFE.2023016

Details

Primary Language

English

Subjects

Data Management and Data Science (Other)

Journal Section

Research Article

Authors

Filiz Erataş Sönmez
0000-0003-2052-340X
Türkiye

Şule Öztürk Birim ^*
0000-0001-7544-8588
Türkiye

Publication Date

March 14, 2026

Submission Date

December 13, 2025

Acceptance Date

March 8, 2026

Published in Issue

Year 2026 Number: 6

DOI

https://doi.org/10.57019/jmv.1841380

IZ

https://izlik.org/JA26LW43AD

Cite

RIS / Bibtex

APA

Erataş Sönmez, F., & Öztürk Birim, Ş. (2026). Exchange Rate Prediction Under Data Volatility: A Comparison Of Deep Learning Techniques. Journal of Metaverse, 6, 100-115. https://doi.org/10.57019/jmv.1841380