Forecasting Turkish Lira (TRY)/US Dollar (USD) Interest Exchange Rates Using Machine Learning Methodologies

Abstract

Machine learning algorithms have become increasingly popular in recent years for analyzing financial data and predicting the exchange rate system. The aim of this paper was to construct an investment appreciation rate estimation model based on machine learning by estimating the Turkish lira/US dollar exchange rate. The forecasting model was developed using foreign exchange market data, namely the exchange rates in TL and USD at specific periods. The proposed model was estimated using machine learning methods such as Multilayer Perceptron (MLP), Linear Regression (LR), Support Vector Machine (SVM), Random Forest (RF), and Local Weighted Learning (LWL). The model's validity was established using TRY interest rates and the USD exchange rate. The data were analyzed using mean absolute error (MAE), directional accuracy (DA), mean square error (MSE), and root mean square error (RMSE). These metric results show that the proposed model is suitable for both prediction and investment data.

Keywords

• Machine Learning
• Exchange Rate Prediction
• Regression
• MLP
• SVM
• RF
• LWL

References

1. M. Štěpnička, P. Cortez, J. P. Donate, and L. Štěpničková, “Forecasting seasonal time series with computational intelligence: On recent methods and the potential of their combinations,” Expert Syst. Appl., vol. 40, no. 6, pp. 1981–1992, 2013, doi: 10.1016/j.eswa.2012.10.001.
2. M. C. Lee, “Using support vector machine with a hybrid feature selection method to the stock trend prediction,” Expert Syst. Appl., vol. 36, no. 8, pp. 10896–10904, 2009, doi: 10.1016/j.eswa.2009.02.038.
3. M. Yasir et al., “An intelligent event-sentiment-based daily foreign exchange rate forecasting system,” Appl. Sci., vol. 9, no. 15, 2019, doi: 10.3390/app9152980.
4. D. Shah, H. Isah, and F. Zulkernine, “Stock market analysis: A review and taxonomy of prediction techniques,” Int. J. Financ. Stud., vol. 7, no. 2, 2019, doi: 10.3390/ijfs7020026.
5. M. J. S. de Souza, D. G. F. Ramos, M. G. Pena, V. A. Sobreiro, and H. Kimura, “Examination of the profitability of technical analysis based on moving average strategies in BRICS,” Financ. Innov., vol. 4, no. 1, 2018, doi: 10.1186/s40854-018-0087-z.
6. F. Cavalli, A. Naimzada, and M. Pireddu, “An evolutive financial market model with animal spirits: imitation and endogenous beliefs,” J. Evol. Econ., vol. 27, no. 5, pp. 1007–1040, 2017, doi: 10.1007/s00191-017-0506-8.
7. J. Contreras, R. Espínola, F. J. Nogales, and A. J. Conejo, “ARIMA models to predict next-day electricity prices,” IEEE Trans. Power Syst., vol. 18, no. 3, pp. 1014–1020, 2003, doi: 10.1109/TPWRS.2002.804943.
8. T. Bollerslev, “Generalized autoregressive conditional heteroskedasticity,” J. Econ., vol. 31, pp. 307–327, 1986, doi: 10.3905/jpm.2019.1.098.

9. M. Khashei and M. Bijari, “An artificial neural network (p, d, q) model for timeseries forecasting,” Expert Syst. Appl., vol. 37, no. 1, pp. 479–489, 2010, doi: 10.1016/j.eswa.2009.05.044.
10. S. Galeshchuk, “Neural networks performance in exchange rate prediction,” Neurocomputing, vol. 172, pp. 446–452, 2016, doi: 10.1016/j.neucom.2015.03.100.
11. B. Amrouche and X. Le Pivert, “Artificial neural network based daily local forecasting for global solar radiation,” Appl. Energy, vol. 130, no. 2014, pp. 333–341, 2014, doi: 10.1016/j.apenergy.2014.05.055.
12. S. Agatonovic-Kustrin and R. Beresford, “Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research,” J. Pharm. Biomed. Anal., vol. 22, no. 5, pp. 717–727, 2000, doi: 10.1016/S0731-7085(99)00272-1.
13. “Investing in Turkey, 2010-2021 | Kaggle.” https://www.kaggle.com/captainozlem/investing-in-turkey-2010-2021/data (accessed Dec. 01, 2021).
14. M. Lam, “Neural network techniques for financial performance prediction : integrating fundamental and technical analysis,” vol. 37, pp. 567–581, 2004, doi: 10.1016/S0167-9236(03)00088-5.
15. Z. Jin, J. Shang, Q. Zhu, C. Ling, W. Xie, and B. Qiang, “RFRSF: Employee Turnover Prediction Based on Random Forests and Survival Analysis,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 12343 LNCS, pp. 503–515, 2020, doi: 10.1007/978-3-030-62008-0_35.
16. Q. H. Luu, M. F. Lau, S. P. H. Ng, and T. Y. Chen, “Testing multiple linear regression systems with metamorphic testing,” J. Syst. Softw., vol. 182, p. 111062, 2021, doi: 10.1016/j.jss.2021.111062.
17. “Multilayer Perceptrons - an overview | ScienceDirect Topics.” https://www.sciencedirect.com/topics/computer-science/multilayer-perceptrons (accessed Dec. 02, 2021).
18. M. A. Ghorbani, R. C. Deo, Z. M. Yaseen, M. H. Kashani, and B. Mohammadi, “Pan evaporation prediction using a hybrid multilayer perceptron-firefly algorithm (MLP-FFA) model: case study in North Iran,” Theor. Appl. Climatol., vol. 133, no. 3–4, pp. 1119–1131, 2018, doi: 10.1007/s00704-017-2244-0.
19. M. A. Ghorbani, R. Khatibi, B. Hosseini, and M. Bilgili, “Relative importance of parameters affecting wind speed prediction using artificial neural networks,” Theor. Appl. Climatol., vol. 114, no. 1–2, pp. 107–114, 2013, doi: 10.1007/s00704-012-0821-9.
20. V. Vapnik, The Nature of Statistical Learning Theory. Springer, New York, 1995.
21. P. Rivas-Perea, J. Cota-Ruiz, D. G. Chaparro, J. A. P. Venzor, A. Q. Carreón, and J. G. Rosiles, “Support Vector Machines for Regression: A Succinct Review of Large-Scale and Linear Programming Formulations,” Int. J. Intell. Sci., vol. 03, no. 01, pp. 5–14, 2013, doi: 10.4236/ijis.2013.31002.
22. Y. Alqasrawi, M. Azzeh, and Y. Elsheikh, “Science of Computer Programming Locally weighted regression with different kernel smoothers for software effort estimation,” vol. 214, pp. 1–17, 2022.
23. S. Schaal, C. G. Atkeson, and S. Vijayakumar, “Real-time robot learning with locally weighted statistical learning,” Proc. - IEEE Int. Conf. Robot. Autom., vol. 1, no. March 2015, pp. 288–293, 2000, doi: 10.1109/robot.2000.844072.
24. N. Mehdiyev, D. Enke, P. Fettke, and P. Loos, “Evaluating Forecasting Methods by Considering Different Accuracy Measures,” Procedia Comput. Sci., vol. 95, pp. 264–271, 2016, doi: 10.1016/j.procs.2016.09.332.
25. A. A. Syntetos and J. E. Boylan, “The accuracy of intermittent demand estimates,” Int. J. Forecast., vol. 21, no. 2, pp. 303–314, 2005, doi: 10.1016/j.ijforecast.2004.10.001.
26. T. M. Usha and S. A. A. Balamurugan, “Seasonal Based Electricity Demand Forecasting Using Time Series Analysis,” Circuits Syst., vol. 07, no. 10, pp. 3320–3328, 2016, doi: 10.4236/cs.2016.710283.
27. I. Moosa and J. Vaz, “Directional accuracy, forecasting error and the profitability of currency trading: model-based evidence,” Appl. Econ., vol. 47, no. 57, pp. 6191–6199, 2015, doi: 10.1080/00036846.2015.1068917.
28. T. Chai and R. R. Draxler, “Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature,” Geosci. Model Dev., vol. 7, no. 3, pp. 1247–1250, 2014, doi: 10.5194/gmd-7-1247-2014.