Bir kriz dönemi Türkiye’sindeki döviz cinsinden mevduatların bir alt kümesinin destek vektör makineleri ile tahmini

Öz

Bu makale, yabancı para (döviz) cinsinden mevduatların, Türkiye’nin iktisadi ve siyasi tarihinin kriz içeren bir konjonktüründeki büyüme hızlarını tahmin etmeye çalışmaktadır. Bu tür konjonktürlerin tahmin süreçleri için yarattığı sorunların, geleneksel istatistiksel yöntemlerin sınırları içinde her zaman etkin bir şeklide çözülememesi, alternatif yöntem kullanımı ihtiyacını ortaya çıkarmaktadır. Bu makale, tahmin için alternatif bir yöntem denemektedir. Kullanılan yöntem, bir makine öğrenmesi/yapay zekâ algoritmaları demeti olan destek vektör makineleridir. Destek vektör makineleri, geniş bir yelpazede başarılı sonuçlar üretebilmektedir. Destek vektör makinelerinin uygun bir kullanımının, makaledeki hedef değişkenin yüksek doğruluk derecesine sahip tahminine ve gerçek değerlerle küçük bir hata marjıyla örtüşen bir yörünge türetimine yol açtığı gösterilmektedir. Döviz cinsinden mevduatların büyüme hızlarının, kriz içeren konjonktürlerde doğru tahmini, ilgili mevduatların miktarlarını ya da büyüme hızlarını optimal bir tarzda sınırlamak isteyen politika yapıcılar için pratik önem taşımaktadır. Bu makale, pratik önem ve değer taşıyan bir amaca, alternatif bir yöntemle nasıl ulaşılabileceğini göstermektedir.

Anahtar Kelimeler

• Döviz cinsinden mevduatlar
• destek vektör makineleri
• tahmin
• Türkiye.

Support vector machine-based and crisis-pertaining forecasts of a subset of foreign currency- denominated bank deposits in Türkiye

Öz

This paper presents support vector machine-based forecasts of a subset of the banking system’s foreign currency-denominated deposit-growth for a crisis-inclusive period in Türkiye. Forecasts concerning such periods pose challenges that may not always be efficiently handled within the confines of conventional statistical methods. This brings out a need to make recourse to alternative methods, one of which is employed in this paper. The method employed in the paper belongs to a particular group of machine learning/artificial intelligence algorithms known as support vector machines, which could yield successful results in a wide range of cases. We demonstrate that proper employment of support vector machines leads to a reasonably high degree of accuracy in forecasting and produces, with a small margin of error, real-value-replicating trajectories of the target variable in question. Accurate forecasts of foreign currency-denominated deposit growth rates at crisis-inclusive junctures could be of practical significance to the policy designers attempting to limit, in an optimal manner, the magnitudes(s) or growth(s) of the foreign currency-denominated deposits within the banking system. This article shows how the objective of practical significance in question could be achieved with an alternative method.

Anahtar Kelimeler

• Foreign currency-denominated deposits
• support vector machines
• forecasting
• Türkiye

Kaynakça

1. Cao, Y. & Chen, X.H. (2012). An agent-based simulation model of enterprises financial distress for the enterprise of different life cycle stage. Simulation Modelling Practice and Theory, 20 (1), 70-88.
2. Chen, A.-P., Huang, C.H. & Hsu, Y.C. (2009). A novel modified particle swarm optimization for forecasting financial time series. In Chen, W., Li, S.Z. & Wang, Y.L. (Eds.) 2009 IEEE International Conference on Intelligent Computing and Intelligent Systems, Proceedings Vol. 1., 683-687.
3. Chiraphadhanakul, S., Dangprasert, P. & Avatchanakorn, V. (1997). Genetic algorithms in forecasting commercial banks deposit. 1997 IEEE International Conference on Intelligent Processing Systems, Vols. 1 & 2, 116-121.
4. Chopra, R. & Sharma, G.D. (2021). Application of artificial intelligence in stock market forecasting: a critique, review, and research agenda. Journal of Risk and Financial Management, 14(11), Article No. 526. DOI: 10.3390/jrfm14110526.
5. Costa, S., Faias, M., Júdice, P. & Mota, P. (2021). Panel data modeling of bank deposits. Annals of Finance, 17(2), 247-264.
6. Ding, Z.X. (2012). Application of support vector machine regression in stock price forecasting. In M. Zhu (Ed.), Proceedings of International Conference on Business, Economics, and Financial Sciences, Management (BEFM 2011), 143, 359-365.
7. Fedyk, T. (2017). Refining financial analysts' forecasts by predicting earnings forecast errors. International Journal of Accounting and Information Management, 25(2): 256-272.
8. Ferrara, L., & Guegan, (2000). D. Forecasting financial times series with generalized long memory processes. In C.L. Dunis (Ed.), Advances in Quantitative Asset Management (pp.319-342. Springer: London.

9. Herrera, T.J.F. & Dominguez, E.D. (2019). A machine learning approach for banks classification and forecast. In K.S. Soliman, Proceedings of 33rd International-Business-Information-Management-Association (IBIMA) Conference, 1149-1159.
10. Hou, S.P., Cai, Z.Z., Wu, J.M., Du, H.W. & Xie, P. (2022). Applying machine learning to the development of prediction models for bank deposit subscription. International Journal of Business Analytics, 9(1), DOI:10.4018/IJBAN.288514
11. Hsu, M.F. & Pai, P.F. (2013). Incorporating support vector machines with multiple criteria decision making for financial crisis analysis. Quality & Quantity, 47(6), 3481-3492.
12. Kara, A. (2000). Reflections on the economics of the historic Great Depression of 1929. Journal of Economic & Social Research, 2(1), 99-102.
13. Kara, A., (2001), On the efficiency of the financial institutions of profit and loss sharing, Journal of Economic & Social Research, 3(2), 99-104.
14. Kara, A. (2023a). Stabilizing instability-suboptimality-and-chaos-prone fluctuations at crisis junctures: Stochastic possibilities for crisis management. International Journal of Finance & Economics, 28, 1772–1786.
15. Kara, A. (2023b). A machine learning approach to financial forecasting: A case study. The Eurasia Proceedings of Educational & Social Sciences (EPESS), 32, 8-12.
16. Kassem, B. and Saleh, M. (2005). “Simulating a banking crisis using a system dynamics model,” Egyptian Informatics Journal, 6(2), 125-145.
17. Minsky, H.P. (2008). Stabilizing an unstable economy. New York: McGraw Hill.
18. Nair, B.B. & Mohandas, V.P. (2015). Artificial intelligence applications in financial forecasting – a survey and some empirical results. Intelligent Decision Technologies – Netherlands, 9 (2), 99-140.
19. Pawelek, B. & Grochowina, D. (2017). Forecasting the bankruptcy of companies: The study on the usefulness of the random subspaces and random forests methods. In M. Papiez & S. Smiech (Eds.), Proceedings of 11th Professor Aleksander Zelias International Conference on Modeling and Forecasting Socio-Economic Phenomena, 300-309.
20. Popkova, E.G. & Parakhina, V.N. (2019). Managing the global financial system on the basis of artificial intelligence: Possibilities and limitations. In E.G. Popkova (Ed.), Future of the Global Financial System: Downfall or Harmony, 57, pp. 939-946. DOI: 10.1007/978-3-030-00102-5_100.
21. Samitas, A., Polyzos, S. & Siriopoulos, C. (2018). Brexit and financial stability: An agent-based simulation. Economic Modelling, 69, 181-192.
22. Scholten, D.G.G. (2016). Explaining the 2008 financial crisis with a system dynamics Model. https://theses.ubn.ru.nl/bitstream/handle/123456789/5093/Scholten%2C_Daan_1.pdf?sequence=1.
23. Sterman, J.D. (2000). Business Dynamics: systems thinking and modeling for a complex world. New York: McGraw-Hill.
24. Teles, G., Rodrigues, J.J.P.C., Rabelo, R. A. L. & Kozlov, S.A. (2021). Comparative study of support vector machines and random forests machine learning algorithms on credit operation. Software: Practice and Experience, 51(12), 2492–2500.
25. Vaiyapuri, T., Priyadarshini, K ., Hemlathadhevi, A. , Dhamodaran, M., Dutta, A.K., Pustokhina, I.V. & Pustokhin, D.A. (2022). Intelligent feature selection with deep learning based financial risk assessment model. CMC-Computers Materials & Continua, 72 (2), 2429-2444.
26. Vogl, M, Rötzel, PG & Homes, S. (2022). Forecasting performance of wavelet neural networks and other neural network topologies: A comparative study based on financial market data sets. Machine Learning with Applications, 8, Article no. 100302. DOI: 10.1016/j.mlwa.2022.100302.
27. Witten, I.H. (2022a). More data mining with WEKA. Online course. https://www.youtube.com/watch?v=iqQn6YfyGs0&list=PLm4W7_iX_v4OMSgc8xowC2h70s-unJKCp
28. Witten, I. H. (2022b). Advanced data mining with WEKA. Online course. https://www.youtube.com/watch?v=Lhw_XcGCTFg&list=PLm4W7_iX_v4Msh-7lDOpSFWHRYU_6H5Kx
29. Xiao, D. & Wang, J. (2020). Complexity behaviors of agent-based financial dynamics by hetero- distance contact process. Nonlinear Dynamics, 100(4), 3867-3886.
30. Yin, L.L., Li, B.L., Li, P. & Zhang, R.B. (2023). Research on stock trend prediction method based on optimized random forest. CAAI Transactions on Intelligence Technology, 8, 274-284.