This study proposes an ensemble deep learning approach that integrates Bagging Ridge (BR) regression with Bi-directional Long Short-Term Memory (Bi-LSTM) neural networks used as base regressors to become a Bi-LSTM BR approach. Bi-LSTM BR was used to predict the exchange rates of 21 currencies against the USD during the pre-COVID-19 and COVID-19 periods. To demonstrate the effectiveness of our proposed model, we compared the prediction performance with several more traditional machine learning algorithms, such as the regression tree, support vector regression, and random forest regression, and deep learning-based algorithms such as LSTM and Bi-LSTM. Our proposed ensemble deep learning approach outperformed the compared models in forecasting exchange rates in terms of prediction error. However, the performance of the model significantly varied during non-COVID-19 and COVID-19 periods across currencies, indicating the essential role of prediction models in periods of highly volatile foreign currency markets. By providing an improved prediction performance and identifying the most seriously affected currencies, this study is beneficial for foreign exchange traders and other stakeholders in that it offers opportunities for potential trading profitability and for reducing the impact of increased currency risk during the pandemic.

Department of Computer Science and Engineering Hajee Mohammad Danesh Science and Technology University Dinajpur 5200 Bangladesh

Department of Economics and Finance University of New Orleans New Orleans LA 70148 USA

Department of Finance and Banking Hajee Mohammad Danesh Science and Technology University Dinajpur 5200 Bangladesh

Department of Finance Performance and Marketing Teesside University International Business School Teesside University Middlesbrough TS1 3BX Tees Valley UK

Science and Research Centre Faculty of Economics and Administration University of Pardubice Studentska 84 Pardubice 532 10 Czech Republic

Zobrazit více v PubMed

Abedin MZ, Guotai C, Moula FE, Azad AS, Khan MSU. Topological applications of multilayer perceptrons and support vector machines in financial decision support systems. International Journal of Finance & Economics. 2019;24(1):474–507. doi: 10.1002/ijfe.1675. DOI

Abedin MZ, Chi G, Uddin MM, Satu MS, Khan MI, Hajek P. Tax default prediction using feature transformation-based machine learning. IEEE Access. 2020;9:19864–19881. doi: 10.1109/ACCESS.2020.3048018. DOI

Ahmed, S, Hassan, S. U., Aljohani, N. R., & Nawaz, R. (2020). FLF-LSTM: A novel prediction system using forex loss function. Applied Soft Computing, 97, 106780.

Akyildirim E, Goncu A, Sensoy A. Prediction of cryptocurrency returns using machine learning. Annals of Operations Research. 2021;297:3–36. doi: 10.1007/s10479-020-03575-y. DOI

Alhagry S, Fahmy AA, El-Khoribi RA. Emotion recognition based on EEG using LSTM recurrent neural network. Emotion. 2017;8(10):355–358.

Aslam, F., Aziz, S., Nguyen, D. K., Mughal, K. S., & Khan, M. (2020). On the efficiency of foreign exchange markets in times of the COVID-19 pandemic. Technological Forecasting and Social Change, 161, 120261. PubMed PMC

Bagheri A, Mohammadi Peyhani H, Akbari M. Financial forecasting using ANFIS networks with quantum-behaved particle swarm optimization. Expert Systems with Applications. 2014;41:6235–6250. doi: 10.1016/j.eswa.2014.04.003. DOI

Balabin RM, Lomakina EI. Support vector machine regression (SVR/LS-SVM)—An alternative to neural networks (ANN) for analytical chemistry? Comparison of non-linear methods on near infrared (NIR) spectroscopy data. The Analyst. 2011;136(8):1703–1712. doi: 10.1039/c0an00387e. PubMed DOI

Bank for International Settlements (2019). Triennial Central Bank Survey.

Bloomberg (2020). Perfect storm plunges Asia stocks into bear markets one by one.

Borovkova S, Tsiamas I. An ensemble of LSTM neural networks for high-frequency stock market classification. Journal of Forecasting. 2019;38(6):600–619. doi: 10.1002/for.2585. DOI

Bradter U, Kunin WE, Altringham JD, Thom TJ, Benton TG. Identifying appropriate spatial scales of predictors in species distribution models with the random forest algorithm. Methods in Ecology and Evolution. 2013;4(2):167–174. doi: 10.1111/j.2041-210x.2012.00253.x. DOI

Bramer, M. (2007). Avoiding overfitting of decision trees. Principles of Data Mining, 119–134.

Breiman L. Random forests. Machine Learning. 2001;45(1):5–32. doi: 10.1023/A:1010933404324. DOI

Carapuço J, Neves E, Horta N. Reinforcement learning applied to Forex trading. Applied Soft Computing. 2018;73:783–794. doi: 10.1016/j.asoc.2018.09.017. DOI

Carta S, Corriga A, Ferreira A, Podda AS, Recupero DR. A multi-layer and multi-ensemble stock trader using deep learning and deep reinforcement learning. Applied Intelligence. 2021;51(2):889–905. doi: 10.1007/s10489-020-01839-5. DOI

Chen M-Y. Predicting corporate financial distress based on integration of decision tree classification and logistic regression. Expert Systems with Applications. 2011;38(9):11261–11272. doi: 10.1016/j.eswa.2011.02.173. DOI

Cheng I-H. Volatility markets underreacted to the early stages of the COVID-19 pandemic. The Review of Asset Pricing Studies. 2020;10(4):635–668. doi: 10.1093/rapstu/raaa010. DOI

Corbet, S., Goodell, J. W., & Günay, S. (2020). Co-movements and spillovers of oil and renewable firms under extreme conditions: New evidence from negative WTI prices during COVID-19. Energy Economics, 104978. PubMed PMC

Cui H, Rajagopalan S, Ward AR. Predicting product return volume using machine learning methods. European Journal of Operational Research. 2020;281(3):612–627. doi: 10.1016/j.ejor.2019.05.046. DOI

Das SR, Mishra D, Rout M. A hybridized ELM using self-adaptive multi-population-based Jaya algorithm for currency exchange prediction: An empirical assessment. Neural Computing and Applications. 2019;31:7071–7094. doi: 10.1007/s00521-018-3552-8. DOI

Dash R. Performance analysis of a higher order neural network with an improved shuffled frog leaping algorithm for currency exchange rate prediction. Applied Soft Computing. 2018;67:215–231. doi: 10.1016/j.asoc.2018.02.043. DOI

Delen D, Kuzey C, Uyar A. Measuring firm performance using financial ratios: A decision tree approach. Expert Systems with Applications. 2013;40(10):3970–3983. doi: 10.1016/j.eswa.2013.01.012. DOI

Diebold FX, Mariano RS. Comparing predictive accuracy. Journal of Business and Economic Statistics. 2002;20(1):134–144. doi: 10.1198/073500102753410444. DOI

Fischer T, Krauss C. Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research. 2018;270(2):654–669. doi: 10.1016/j.ejor.2017.11.054. DOI

Galeshchuk, S. Neural networks performance in exchange rate prediction. Neurocomputing, 172, 446–452.

Gazzola G, Jeong MK. Support vector regression for polyhedral and missing data. Annals of Operations Research. 2021;303:483–506. doi: 10.1007/s10479-020-03799-y. DOI

Guotai C, Abedin MZ, Moula FE. Modeling credit approval data with neural networks: An experimental investigation and optimisation. Journal of Business Economics and Management. 2017;18(2):224–240. doi: 10.3846/16111699.2017.1280844. DOI

Hajek P, Abedin MZ. A profit function-maximizing inventory backorder prediction system using big data analytics. IEEE Access. 2020;8:58982–58994. doi: 10.1109/ACCESS.2020.2983118. DOI

Hennig, M., Grafinger, M., Hofmann, R., Gerhard, D., Dumss, S., & Rosenberger, P. (2021). Introduction of a time series machine learning methodology for the application in a production system. Advanced Engineering Informatics, 47, 101197.

Hochreiter S, Schmidhuber J. Long short-term memory. Neural Computation. 1997;9(8):1735–1780. doi: 10.1162/neco.1997.9.8.1735. PubMed DOI

Hofmann, B., Shim, I., & Shin, H. S. (2020). Emerging market economy exchange rates and local currency bond markets amid the Covid-19 pandemic. Available at SSRN: https://ssrn.com/abstract=3761875

Hsu C-W, Lin C-J. A comparison of methods for multiclass support vector machines. IEEE Transactions on Neural Networks. 2002;13(2):415–425. doi: 10.1109/72.991427. PubMed DOI

IMF (2021). World Economic Outlook Update, July 2021.

Islam MS, Hossain E. Foreign exchange currency rate prediction using a GRU-LSTM Hybrid Network. Soft Computing Letters. 2020 doi: 10.1016/j.socl.2020.100009. DOI

Jiang M, Jia L, Chen Z, Chen W. The two-stage machine learning ensemble models for stock price prediction by combining mode decomposition, extreme learning machine and improved harmony search algorithm. Annals of Operations Research. 2020 doi: 10.1007/s10479-020-03690-w. DOI

Kyriakou I, Mousavi P, Nielsen JP, Scholz M. Forecasting benchmarks of long-term stock returns via machine learning. Annals of Operations Research. 2021;297:221–240. doi: 10.1007/s10479-019-03338-4. DOI

Lahmiri S. Modeling and predicting historical volatility in exchange rate markets. Physica A: Statistical Mechanics and Its Applications. 2017;471:387–395. doi: 10.1016/j.physa.2016.12.061. DOI

Mahmoud E, Hosseini H. A comparison of forecasting techniques for predicting exchange rates. Journal of Transnational Management Development. 1994;1(1):93–110. doi: 10.1300/J130v01n01_07. DOI

Mathew, A., Amudha, P., & Sivakumari, S. Deep learning techniques: An overview. In International Conference on Advanced Machine Learning Technologies and Applications, 2020 (pp. 599–608). Springer.

Maya C, Gómez K. What exactly is' Bad News' in foreign exchange markets?: Evidence from Latin American markets. Cuadernos De Economía. 2008;45(132):161–183.

Munkhdalai L, Munkhdalai T, Park KH, Lee HG, Li M, Ryu KH. Mixture of activation functions with extended min-max normalization for forex market prediction. IEEE Access. 2019;7:183680–183691. doi: 10.1109/ACCESS.2019.2959789. DOI

Narayan PK. Has COVID-19 changed exchange rate resistance to shocks? Asian Economics Letters. 2020;1(1):17389.

Özorhan MO, Toroslu İH, Şehitoğlu OT. Short-term trend prediction in financial time series data. Knowledge and Information Systems. 2019;61:397–429. doi: 10.1007/s10115-018-1303-x. DOI

Panda C, Narasimhan V. Forecasting exchange rate better with artificial neural network. Journal of Policy Modeling. 2007;29(2):227–236. doi: 10.1016/j.jpolmod.2006.01.005. DOI

Panda, M. M., Panda, S. N., & Pattnaik, P. K. (2021). Multi currency exchange rate prediction using convolutional neural network. Materials Today: Proceedings. 10.1016/j.matpr.2020.11.317

Provost F, Hibert C, Malet J-P, Stumpf A, Doubre C. Automatic classification of endogenous seismic sources within a landslide body using random forest algorithm. EGUGA, EPSC. 2016;2016:15705.

Rambaldi, M., Pennesi, P., & Lillo, F. (2015). Modeling foreign exchange market activity around macroeconomic news: Hawkes-process approach. Physical Review E, 91(1), 012819. PubMed

Ribeiro, V. H. A., Reynoso-Meza, G., & Siqueira, H. V. (2020). Multi-objective ensembles of echo state networks and extreme learning machines for streamflow series forecasting. Engineering Applications of Artificial Intelligence, 95, 103910.

Rundo, F. (2019) Deep LSTM with reinforcement learning layer for financial trend prediction in FX high frequency trading systems. Applied Sciences, 9, 4460.

Salisu AA, Ebuh GU, Usman N. Revisiting oil-stock nexus during COVID-19 pandemic: Some preliminary results. International Review of Economics and Finance. 2020;69:280–294. doi: 10.1016/j.iref.2020.06.023. DOI

Salisu, A. A., Vo, X. V., & Lawal, A. (2020b). Hedging oil price risk with gold during COVID-19 pandemic. Resources Policy, 70, 101897. PubMed PMC

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.

Shajalal M, Hajek P, Abedin MZ. Product backorder prediction using deep neural network on imbalanced data. International Journal of Production Research. 2021 doi: 10.1080/00207543.2021.1901153. DOI

Shen F, Chao J, Zhao J. Forecasting exchange rate using deep belief networks and conjugate gradient method. Neurocomputing. 2015;167:243–253. doi: 10.1016/j.neucom.2015.04.071. DOI

Sun, S., Wang, S., & Wei, Y. (2020). A new ensemble deep learning approach for exchange rates forecasting and trading. Advanced Engineering Informatics, 46, 101160.

Sunny, M. A. I., Maswood, M. M. S., & Alharbi, A. G. Deep Learning-Based Stock Price Prediction Using LSTM and Bi-Directional LSTM Model. In 2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES), 2020 (pp. 87–92). IEEE.

The Guardian. (2020). FTSE 100 suffers worst quarter since 1987 as Covid-19 recession looms—as it happened.

The Reserve Bank of Australia. (2020). The Response by Central Banks in Advanced Economies to COVID-19.

Umar, Z., & Gubareva, M. (2020). A time–frequency analysis of the impact of the Covid-19 induced panic on the volatility of currency and cryptocurrency markets. Journal of Behavioral and Experimental Finance, 28, 100404. PubMed PMC

Weston J, Gammerman A, Stitson M, Vapnik V, Vovk V, Watkins C. Density estimation using support vector machines. University of London; 1997.

Windsor C, Thyagaraja A. The prediction of periods of high volatility in exchange markets. The European Physical Journal B-Condensed Matter and Complex Systems. 2001;20(4):581–584. doi: 10.1007/PL00011111. DOI

World Economic Forum (2020). Mad March: How the stock market is being hit by COVID-19.

Xia H, Liu J, Zhang ZJ. Identifying Fintech risk through machine learning: Analysing the Q&A text of an online loan investment platform. Annals of Operations Research. 2020 doi: 10.1007/s10479-020-03842-y. DOI

Yao J, Tan CL. A case study on using neural networks to perform technical forecasting of forex. Neurocomputing. 2000;34:79–98. doi: 10.1016/S0925-2312(00)00300-3. DOI

Yıldırım DC, Toroslu IH, Fiore U. Forecasting directional movement of Forex data using LSTM with technical and macroeconomic indicators. Financial Innovation. 2021;7(1):1–36. doi: 10.1186/s40854-020-00220-2. DOI

Yoshino, N., Taghizadeh-Hesary, F., & Otsuka, M. (2021). Covid-19 and optimal portfolio selection for investment in sustainable development goals. Finance Research Letters, 38, 101695. PubMed PMC

An interpretable system for predicting the impact of COVID-19 government interventions on stock market sectors