USD/TRY DÖVİZ KURU TAHMİNİNDE MAKİNE VE DERİN ÖĞRENME YÖNTEMLERİNİN PERFORMANS KARŞILAŞTIRMASI

Yıl 2024, Cilt: 15 Sayı: 3, 1473 - 1499, 31.12.2024

Ahmed İhsan Şimşek

https://doi.org/10.54688/ayd.1519303

Öz

Döviz kurlarının doğru bir şekilde tahmin edilmesi ekonomik ve finansal analizler açısından oldukça önemlidir. Türkiye özellikle son dönemde ciddi döviz kuru dalgalanmaları ile karşı karşıya kalmaktadır. Bu noktada döviz kurlarının doğru bir şekilde tahmin edilmesi hem bireysel hem de kurumsal yatırımcılar için büyük önem taşımaktadır. Bu çalışmada USD/TRY kurunun tahmini Ocak 2012-Mayıs 2024 tarihleri arasındaki 149 aylık veri kullanılmıştır. Çalışmada girdi değişkenleri olarak Total Opened USD Deposits, M3 para arzı, toplam ithalat, toplam ihracat, işsizlik oranı, altın fiyatı, tüfe, üfe ve merkez bankası net dolar rezervi kullanılmıştır. Çalışmada XGBoost, RandomForest, LightGBM, LSTM ve SVR yöntemleri kullanılarak tahminler yapılmıştır. Ayrıca beş katlı çapraz doğrulama ile elde edilen sonuçların genellenebilirliği test edilmiştir. Elde edilen sonuçlara göre eğitim, test ve çapraz doğrulama veri setleri için en iyi tahmin performansı Random Forest modeli tarafından üretilmiştir.

Anahtar Kelimeler

Döviz kuru, Derin öğrenme, Makine öğrenmesi, Karar destek, Random forest.

PERFORMANCE COMPARISON OF MACHINE AND DEEP LEARNING METHODS IN USD/TRY EXCHANGE RATE FORECASTING

Öz

Accurate estimation of exchange rates is very important for economic and financial analysis. Türkiye has been facing serious exchange rate fluctuations, especially recently. At this point, accurate prediction of exchange rates is of great importance for both individual and institutional investors. In this study, 149 months of data between January 2012 and May 2024 were used to estimate the USD/TRY exchange rate. Total Opened USD Deposits, M3 money supply, total imports, total exports, unemployment rate, gold price, CPI, PPI and central bank net dollar reserve were used as input variables in the study. In the study, predictions were made using XGBoost, RandomForest, LightGBM, LSTM and SVR methods. Additionally, the generalizability of the results obtained with five-fold cross-validation was tested. According to the results obtained, the best prediction performance for training, testing and cross-validation data sets was produced by the Random Forest model.

Anahtar Kelimeler

Exchange Rate, Deep Learning, Machine Learning, Decision Support, Random Forest

Kaynakça

• Abedin, M. Z., Moon, M. H., Hassan, M. K., & Hajek, P. (2021). Deep learning-based exchange rate prediction during the COVID-19 pandemic. Annals of Operations Research, 1-52.
• Agarwal, S. (2022). Deep learning in financial analytics: Exchange rate modelling. Indian Journal of Finance, 16(9), 8 25. https://doi.org/ 10.170 I 0/ijf/2022/v l 6i9/ l 72 l 57
• Amat, C., Michalski, T., & Stoltz, G. (2018). Fundamentals and exchange rate forecastability with simple machine learning methods. Journal of International Money and Finance, 88, 1-24.
• Ata, O., & Erbudak, A. E. (2022). Veri Madenciliği ve Makine Öğrenimi ile Döviz Kuru Tahmini Uygulaması. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 34(2), 553-563.
• Bağcı, B. (2020). Hareketli ortalamalar ve üssel düzeltme yöntemlerinin tahmin gücünün artirilmasi: türkiye’de döviz kuru tahmini. Turkuaz Uluslararası Sosyo-Ekonomik Stratejik Araştırmalar Dergisi, 2(1), 1-12.
• Bao, W., Yue, J., & Rao, Y. (2017). A deep learning framework for financial time series using stacked autoencoders and long-short term memory. PloS one, 12(7), e0180944.
• Breiman, L. (2001). Random forests. Machine learning, 45, 5-32.
• Cao, W., Zhu, W., Wang, W., Demazeau, Y., & Zhang, C. (2020). A deep coupled lstm approach for usd/cny exchange rate forecasting. Ieee Intelligent Systems, 35(2), 43-53. https://doi.org/10.1109/mis.2020.2977283
• Chen, S., Jin, H., & Li, L. (2023). Analysis and comparison of house price prediction based on xgboost and lightgbm. Advances in Economics, Management and Political Sciences, 46(1), 55-61. https://doi.org/10.54254/2754-1169/46/20230317
• Chen, T., & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). New York, NY, USA: Association for Computing Machinery. https://doi.org/10.1145/2939672.2939785
• Chen, W., Li, Y., Xue, W., Shahabi, H., Li, S., Hong, H., ... & Ahmad, B. B. (2020). Modeling flood susceptibility using data-driven approaches of naïve bayes tree, alternating decision tree, and random forest methods. Science of The Total Environment, 701, 134979
• Clavería, O., Monte, E., Sorić, P., & Porras, S. (2022). An application of deep learning for exchange rate forecasting. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.4024308
• Das, S. R., Mishra, D., & Rout, M. (2019). A hybridized ELM using self-adaptive multi-population-based Jaya algorithm for currency exchange prediction: an empirical assessment. Neural Computing and Applications, 31(11), 7071-7094.
• Gümüş, E. (2024). Yapay sinir ağları ve derin öğrenme modeli kullanılarak usd/try döviz kurunun tahmin edilmesi. Anadolu Üniversitesi Sosyal Bilimler Dergisi, 24(2), 703-726.
• Gür, Y. E. (2024). Comparative Analysis of Deep Learning Models for Silver Price Prediction: CNN, LSTM, GRU and Hybrid Approach. Akdeniz İİBF Dergisi, 24(1), 1-13.
• Gür, Y. E. (2024). FORECASTING THE EURO EXCHANGE RATE USING DEEP LEARNING ALGORITHMS AND MACHINE LEARNING ALGORITHMS. İstanbul Ticaret Üniversitesi Sosyal Bilimler Dergisi, 23(49), 1435-1456.
• Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780.
• Karasu, S., Altan, A., Saraç, Z., & Hacioğlu, R. (2018, May). Prediction of Bitcoin prices with machine learning methods using time series data. In 2018 26th signal processing and communications applications conference (SIU) (pp. 1-4). IEEE.
• Kaushik, M., & Giri, A. K. (2020). Forecasting foreign exchange rate: A multivariate comparative analysis between traditional econometric, contemporary machine learning & deep learning techniques. arXiv preprint arXiv:2002.10247.
• Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., ... & Liu, T. Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. Advances In Neural Information Processing Systems, 30.
• Li, H. B., Wang, W., Ding, H., & Dong, J. (2010). Trees weighting random forest method for classifying high-dimensional noisy data. 2010 IEEE 7th International Conference on E-Business Engineering. https://doi.org/10.1109/icebe.2010.99
• Liu, Q., Cui, B., & Liu, Z. (2024). Air quality class prediction using machine learning methods based on monitoring data and secondary modeling. Atmosphere, 15(5), 553. https://doi.org/10.3390/atmos15050553
• Liu, X., Zhao, K., Liu, Z., & Wang, L. (2023). Pm2.5 concentration prediction based on lightgbm optimized by adaptive multi-strategy enhanced sparrow search algorithm. Atmosphere, 14(11), 1612. https://doi.org/10.3390/atmos14111612
• Luo, Y. (2024). Application of deep learning algorithms in predicting the exchange rate of chinese yuan against the us dollar. Applied and Computational Engineering, 52(1), 170-176. https://doi.org/10.54254/2755- 2721/52/20241539
• Manurung, A. H., Suhartono, D., Hutahayan, B., & Halimawan, N. (2023). Probability bankruptcy using support vector regression machines. Journal of Applied Finance & Banking, 13(1), 13-25.
• Nas, S., & Ünal, A. E. (2023). Bitcoin Fiyat Değişimlerinin Makine Öğrenmesi Yöntemi ile Tahmin Edilmesi. İşletme Araştırmaları Dergisi, 15(4), 2597-2608.
• Nguyen, M. and Kim, Y. (2019). Bidirectional long short-term memory neural networks for linear sum assignment problems. Applied Sciences, 9(17), 3470. https://doi.org/10.3390/app9173470
• Park, S., Son, S., Bae, J., Lee, D., & Kim, J. (2021). Robust spatiotemporal estimation of pm concentrations using boosting-based ensemble models. Sustainability, 13(24), 13782. https://doi.org/10.3390/su132413782
• Plakandaras, V., Papadimitriou, T., & Gogas, P. (2015). Forecasting daily and monthly exchange rates with machine learning techniques. Journal of Forecasting, 34(7), 560-573.
• Ramakrishnan, S., Butt, S., Chohan, M. A., & Ahmad, H. (2017, July). Forecasting Malaysian exchange rate using machine learning techniques based on commodities prices. In 2017 International Conference on Research and Innovation in Information Systems (ICRIIS) (pp. 1-5). IEEE.
• 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.
• Rossi, B. (2013). Exchange rate predictability. Journal of economic literature, 51(4), 1063-1119.
• Safi, S., Aliyu, S., Ibrahim, K., & Sanusi, O. (2022). Can oil price predict exchange rate? empirical evidence from deep learning. International Journal of Energy Economics and Policy, 12(4), 482-493. https://doi.org/10.32479/ijeep.13200
• Shakeel, A., Chong, D., & Wang, J. (2023). District heating load forecasting with a hybrid model based on LightGBM and FB-prophet. Journal of Cleaner Production, 409, 137130.
• Sumargo, R., & Wasito, I. (2024). Deep Learning for Exchange Rate Prediction Within Time Constrain. Sinkron: jurnal dan penelitian teknik informatika, 8(3), 1259-1271.
• Sun, S., Wang, S., & Wei, Y. (2020). A new ensemble deep learning approach for exchange rates forecasting and trading. Advanced Engineering Informatics, 46, 101160.
• Tekin, T. G., & Patır, S. (2023). Amerikan doları kurunun yapay sinir ağlari yöntemiyle tahminlenmesi: 2009–2021 dönemi. R&S-Research Studies Anatolia Journal, 6(1), 56-77.
• Ulenberg, S., Belka, M., & Bączek, T. (2016). Comparison of mlr, opls, and svm as potent chemometric techniques used to estimate in vitro metabolic stability. Journal of Chemometrics, 30(4), 177-181. https://doi.org/10.1002/cem.2782
• Wang, L., Song, M., Liu, S., Wang, B., Chen, S., Hu, T., … & Hu, W. (2022). An effective algorithm for offshore air temperature prediction with lstm neural network and wavelet decomposition and reconstruction. Journal of Physics: Conference Series, 2414(1), 012016. https://doi.org/10.1088/1742-6596/2414/1/012016
• Wang, L., Wang, H., & Liu, L. (2022). Body shape recognition and prototype construction based on lightgbm algorithm. Advances in Transdisciplinary Engineering. https://doi.org/10.3233/atde220011
• Yasar, H. and Kilimci, Z. (2020). Us dollar/turkish lira exchange rate forecasting model based on deep learning methodologies and time series analysis. Symmetry, 12(9), 1553. https://doi.org/10.3390/sym12091553
• Yilmaz, F. M., & Arabaci, O. (2021). Should deep learning models be in high demand, or should they simply be a very hot topic? A comprehensive study for exchange rate forecasting. Computational Economics, 57(1), 217-245.
• Yu, X. (2023). Rmb exchange rate forecasting using machine learning methods: can multimodel select powerful predictors?. Journal of Forecasting, 43(3), 644-660. https://doi.org/10.1002/for.3054
• Zhang, Y., & Hamori, S. (2020). The predictability of the exchange rate when combining machine learning and fundamental models. Journal of Risk and Financial Management, 13(3), 48.