Forecasting and Evaluation of Non-Performing Loans in the Turkish Banking Sector

Yıl 2023, Cilt: 52 Sayı: 2, 381 - 406, 28.11.2023

Hazar Altınbaş , Gülay Selvi Hanişoğlu

https://doi.org/10.26650/ibr.2023.52.994354

Öz

In recent years, there is an increasing trend in non-performing loan levels in Turkey which causes stress both on the real and financial sectors. Increasing non-performing loan volumes are an indication of problems in sectors or the general economy. It is also closely related with the stability of the banking system. It is therefore important for regulatory/ supervisory institutions and banks to be able to predict problematic loan levels successfully, for better policy making and management. For this purpose, non-performing loans to credit ratio in Turkey for the dates between the first quarter of 2015 and fourth quarter of 2019 were forecasted with two machine learning methods, namely random forests and boosted trees, by using data starting from the first quarter of 2003. Lagged values of several macroeconomic, bankspecific and uncertainty factors are included as determinant variables in the analyses. Methods provide insight about the relationship of included variables with non-performing loans. Our results indicate partial dependencies and positive relationship between non-performing loans and inflation, interest rate and capital adequacy ratios, and negative relationship with credit to gross domestic product ratio.

Anahtar Kelimeler

Banking Regulations, Financial System, Time-Series Forecasting, Machine Learning

Kaynakça

• Aiyar, M. S., Bergthaler, M. W., Garrido, J. M., Ilyina, M. A., Jobst, A., Kang, M. K., ... Moretti, M. M. (2015). A strategy for resolving Europe’s problem loans. International Monetary Fund. google scholar
• Altınbaş, H. (2020). Modern kredi sınıflandırma çalışmaları ve metasezgisel algoritma uygulamaları: Sistematik bir derleme (Metaheuristic algorithms and modern credit classification methods: A systematic review). İstanbul Business Research, 49(1), 146-175. https://doi.org/10.26650/ibr.2020.49.0033 google scholar
• Arrawatia, R., Dawar, V., Maitra, D., & Dash, S. R. (2019). Asset quality determinants of Indian banks: Em-pirical evidence and policy issues. Journal of Public Affairs, 19(4), e1937. google scholar
• Balgova, M., Nies, M., & Plekhanov, A. (2016). The economic impact of reducing non-performing loans. google scholar
• Banking Regulation and Supervision Agency of Turkey. (2019). Turkish Banking Sector Main Indicators. google scholar
• Bellotti, A., Brigo, D., Gambetti, P., & Vrins, F. (2021). Forecasting recovery rates on non-performing loans with machine learning. International Journal of Forecasting, 37(1), 428-444. google scholar
• Berger, A. N., & DeYoung, R. (1997). Problem loans and cost efficiency in commercial banks. Journal of Banking & Finance, 21(6), 849-870. google scholar
• Bergmeir, C., Hyndman, R. J., & Koo, B. (2018). A note on the validity of cross-validation for evaluating autoregressive time series prediction. Computational Statistics and Data Analysis, 120, 70-83. https://doi. org/10.1016/j.csda.2017.11.003 google scholar
• Boudriga, A., Taktak, N. B., & Jellouli, S. (2009). Banking supervision and nonperforming loans: a cross-country analysis. Journal of Financial Economic Policy. google scholar
• Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5-32. google scholar
• Cerqueira, V., Torgo, L., & Mozetic, I. (2020). Evaluating time series forecasting models: an empirical study on performance estimation methods. Machine Learning, 109(11), 1997-2028. https://doi.org/10.1007/ s10994-020-05910-7 google scholar
• Chai, T., & Draxler, R. R. (2014). Root mean square error (RMSE) or mean absolute error (MAE)? -Ar-guments against avoiding RMSE in the literature. Geoscientific Model Development, 7(3), 1247-1250. https://doi.org/10.5194/gmd-7-1247-2014 google scholar
• Changqing Cheng, Akkarapol Sa-Ngasoongsong, Omer Beyca, Trung Le, Hui Yang, Zhenyu (James) Kong & Satish T.S. Bukkapatnam (2015) Time series forecasting for nonlinear and non-stationary processes: a re-view and comparative study, IIE Transactions, 47:10, 1053-1071, DOI: 10.1080/0740817X.2014.999180 google scholar
• Dimitrios, A., Helen, L., & Mike, T. (2016). Determinants of non-performing loans: Evidence from Euro-area countries. Finance Research Letters, 18, 116-119. https://doi.org/10.1016/j.frl.2016.04.008 google scholar
• European Central Bank Banking Supervision. (2017). Guidance to banks on non-performing loans. google scholar
• Finansal Yeniden Yapılandırma Koordinasyon Sekreteryası. (2005). İstanbul yaklaşımı: Bir yeniden yapılandırma deneyimi (Istanbul approach: A restructuring experience). google scholar
• Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29(5), 1189-1232. google scholar
• Gormez, Y. (2008). Banking in Turkey: history and evolution. google scholar
• Greenidge, K., & Grosvenor, T. (2010). Forcasting non-performing loans in Barbados. Journal of Business, Finance & Economics in Emerging Economies, 5(1). google scholar
• Greenwell, B., Boehmke, B., Cunningham, J., & GBM Developers. (2020). gbm: Generalized boosted reg-ression models. google scholar
• Hastie, T., Tibshirani, R., & Friedman, J. (2009). The Elements of Statistical Learning: Data Mining, Infe-rence, and Prediction (Second). Springer Science & Business Media.Khan, I., Ahmad, A., Khan, M. T., & Ilyas, M. (2018). The impact of GDP, inflation, exchange rate, unemployment and tax rate on the non performing loans of banks: Evidence from Pakistani commercial banks. Journal of Social Sciences and Humanities, 26(1). google scholar
• Kılıç Depren, S., & Kartal, M. T. (2021). Prediction on the volume of non-performing loans in Turkey using multivariate adaptive regression splines approach. International Journal of Finance & Economics, 26(4), 6395-6405. google scholar
• Kjosevski, J., Petkovski, M., & Naumovska, E. (2019). Bank-specific and macroeconomic determinants of non-performing loans in the Republic of Macedonia: Comparative analysis of enterprise and household NPLs. Economic Research-Ekonomska Istrazivanja, 32(1), 1185-1203. google scholar
• Kozaric, K., & Zunic, E. (2015). Causes and consequences of NPLs in Bosnia and Herzegovina banking sector. Journal of Economic and Social Studies, 5(1), 127-144 google scholar
• Kuhn, M., & Johnson, K. (2013). Applied predictive modeling (26th ed.). New York: Springer. google scholar
• Liaw, A., & Wiener, M. (2002). Classification and regression by randomForest. R News, 2(3), 18-22. https:// doi.org/10.1023/A:1010933404324 google scholar
• Lopez De Prado, M. (2018). The 10 Reasons Most Machine Learning Funds Fail. The Journal of Portfolio Management, 44(6), 120-133. Retrieved from www.TruePositive.com google scholar
• Louzis, D. P., Vouldis, A. T., & Metaxas, V. L. (2012). Macroeconomic and bank-specific determinants of non-performing loans in Greece: A comparative study of mortgage, business and consumer loan portfoli-os. Journal ofBanking & Finance, 36(4), 1012-1027. google scholar
• Makri, V., Tsagkanos, A., & Bellas, A. (2014). Determinants of non-performing loans: The case of Eurozone. Panoeconomicus, 61(2), 193-206. https://doi.org/10.2298/PAN1402193M google scholar
• Messai, A. S., & Jouini, F. (2013). Micro and Macro Determinants of Non-performing Loans. International Journal ofEconomics and Financial Issues, 3(4), 852-860. Retrieved from www.econjournals.com google scholar
• Mishkin, F. S. (2007). The economics of money, banking, and financial markets. Pearson education. google scholar
• Munteanu, I. (2012). Bank Liquidity and its Determinants in Romania. Emerging Market Queries in Finance and Business, 993-998. google scholar
• Nkusu, M. (2011). Nonperforming loans and macrofinancial vulnerabilities in advanced economies. IMF Working Papers, 1-27. google scholar
• Orhangazi, Ö. (2014). Capital flows and credit expansions in Turkey. Review ofRadical Political Economics, 46(4), 509-516. google scholar
• Ozatay, F., & Sak, G. (2002). Banking sector fragility and Turkey’s 2000-01 financial crisis. Brookings Trade Forum, 2002(1), 121-160. google scholar
• Ozili, P. K. (2019). Non-performing loans and financial development: new evidence. The Journal of Risk Finance. google scholar
• Podpiera, J., & Weill, L. (2008). Bad luck or bad management? Emerging banking market experience. Jour-nal ofFinancial Stability, 4(2), 135-148. google scholar
• Poudel, R. P. S. (2012). The impact of credit risk management on financial performance of commercial banks in Nepal. International Journal ofArts and Commerce, 1(5), 9-15. google scholar
• R Core Team. (2020). R: A language and environmentfor statistical computing. Vienna, Austria: R Founda-tion for Statistical Computing. google scholar
• Reinhart, C. M., & Rogoff, K. S. (2011). From financial crash to debt crisis. American Economic Review, 101(5), 1676-1706. google scholar
• Salas, V., & Saurina, J. (2002). Credit risk in two institutional regimes: Spanish commercial and savings banks. Journal ofFinancial Services Research, 22(3), 203-224. google scholar
• Scornet, E. (2018). Tuning parameters in random forests. ESAIM: Proceedings and Surveys, 60, 144-162. EDP Sciences. https://doi.org/10.1051/proc/201760144 google scholar
• The Banks Association of Turkey. (2019). Framework agreements on financial restructuring. Retrieved January 17, 2021, from https://www.tbb.org.tr/en/banking-legislation/professional-codes-/framework-agreements-on-financial-restructuring/91 google scholar
• The European Systemic Risk Board. (2019). Macroprudential approaches to non-performing loans. google scholar
• Us, V. (2018). The determinants of nonperforming loans before and after the crisis: Challenges and policy implications for Turkish banks. Emerging Markets Finance and Trade, 54(7), 1608-1622. google scholar
• Vatansever, M., & Hepsen, A. (2013). Determining impacts on non-performing loan ratio in Turkey. Journal of 'Finance andInvestmentAnalysis, 2(4), 119-129. google scholar
• Willmott, C. J., & Matsuura, K. (2005). Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate Research, 30(1), 79-82. Retrie-ved from www.int-res.com google scholar
• Woo, D. (2000). Two approaches to resolving nonperforming assets during financial crises. google scholar
• Yentürk, N. (1999). Short-term capital inflows and their impact on macroeconomic structure: Turkey in the 1990s. The Developing Economies, 37(1), 89-113. google scholar