DOI :10.26650/B/SS10.2023.001.10   IUP :10.26650/B/SS10.2023.001.10    Full Text (PDF)

Predicting the Probability of Default with the Help of Macroeconomic Indicators in IFRS 9 Provision Calculations

Muhammed IşıkBahar SennaroğluMine Genç

IFRS 9 process has a significant issue for banks. IFRS 9 process assists banks in calculating and managing their mandatory provision. The probability of Default is one of the essential parameters in the IFRS 9 process. This process has two different Probabilities of Default (Through-The-Cycle and Point-In-Time). However, Point-In-Time Probability of Default, where only macroeconomic effects are reflected, is used in the required provision calculation. Through-The-Cycle Probability of Default cannot be used directly for provision calculation. Point-In-Time Probability of Default will be obtained by reflecting macroeconomic effects. In this study, it has been provided to convert Through-The-Cycle Probability of Default to Point-In-Time Probability of Default. Relief Approach and Genetic Algorithm (Evolutionary Search) were used in the feature selection stage. k–Nearest Neighbors, MultiLayer Perceptron, and Extreme Gradient Boosting were used during the creation of the model. In this study, contemporary feature selection and modeling techniques were applied to the data set, and the results were compared. In this study, contemporary regression models used seem to be quite successful.


  • Aptivaa (2016) Building Blocks of Impairment Modeling (Issue 02). Available at: google scholar
  • Bellini, T. (2019) IFRS 9 and CECL Credit Risk Modelling and Validation. 1st edition. San Diego, CA: Elsevier. google scholar
  • Beque, A. and Lessmann, S. (2017) ‘Extreme Learning Machines for Credit Scoring: An Empirical Evaluation, Expert Systems with Applications, 86, pp. 42-53. doi:10.1016/j.eswa.2017.05.050. google scholar
  • Brezigar-Masten, A., Masten, I. and Volk, M. (2021) ‘Modeling Credit Risk with a Tobit Model of Days Past Due,’ Journal of Banking & Finance, 122, p. 105984. doi:10.1016/j.jbankfin.2020.105984. google scholar
  • Chang, Y.-C., Chang, K.-H. and Wu, G.-J. (2018) ‘Application of eXtreme Gradient Boosting Trees in the Construction of Credit Risk Assessment Models for Financial Institutions,’ Applied Soft Computing, 73, pp. 914-920. doi:10.1016/j.asoc.2018.09.029. google scholar
  • Climent, F., Momparler, A. and Carmona, P. (2019) ‘Anticipating Bank Distress in the Eurozone: An Extreme Gradient Boosting approach,’ Journal of Business Research, 101, pp. 885-896. doi:10.1016/j. jbusres.2018.11.015. google scholar
  • Feuerriegel, S. and Gordon, J. (2019) ‘News-Based Forecasts of Macroeconomic Indicators: A Semantic Path Model for Interpretable Predictions,’ European Journal of Operational Research, 272(1), pp. 162-175. doi:10.1016/j.ejor.2018.05.068. google scholar
  • Filusch, T. (2021) ‘Risk assessment for financial accounting: modeling probability of default,’ The Journal of Risk Finance, 22(1), pp. 1-15. doi:10.1108/JRF-02-2020-0033. google scholar
  • Gil-Cordero, E. and Cabrera-Sanchez, J.-P. (2020) ‘Private Label and Macroeconomic Indexes: An Artificial Neural Networks Application,’ Applied Sciences, 10(17), p. 6043. doi:10.3390/app10176043. google scholar
  • Huang, J. and Perry, M. (2016) ‘A semi-empirical approach using gradient boosting and k -nearest neighbors regression for GEFCom2014 probabilistic solar power forecasting, International Journal of Forecasting, 32(3), pp. 1081-1086. doi:10.1016/j.ijforecast.2015.11.002. google scholar
  • Ingolfsson, S. and Elvarsson, B.T. (2010) ‘Cyclical adjustment of point-in-time PD,’ Journal of the Operational Research Society, 61(3), pp. 374-380. doi:10.1057/jors.2009.136. google scholar
  • Işık, M. (2021a) ‘Dataset’. Available at: Işık, Muhammed (2021), “IFRS_9_Macroeconomic_Model_Training Dataset”, Mendeley Data, V2, DOI: 10.17632/4d4bxpyf87.2. google scholar
  • Işık, M. (2021b) Modeling. Available at: IŞIK. (2021, June 30). IFRS 9 Macroeconomic Modeling. Zenodo. google scholar
  • Ito, T. et al. (2020) ‘A Fast Approximation of the Nadaraya-Watson Regression with the k-Nearest Neighbor Crossover Kernel,’ in. 2020 7th International Conference on Soft Computing & Machine Intelligence (ISCMI), Stockholm, Sweden: IEEE, pp. 39-44. doi:10.1109/ISCMI51676.2020.9311579. google scholar
  • Jadhav, S., He, H. and Jenkins, K. (2018) ‘Information Gain Directed Genetic Algorithm Wrapper Feature Selection for Credit Rating,’ Applied Soft Computing, 69, pp. 541-553. doi:10.1016/j.asoc.2018.04.033. google scholar
  • Khan, Z.A. et al. (2020) ‘Short Term Electricity Price Forecasting Through Convolutional Neural Network (CNN),’ Web, Artificial Intelligence and Network Applications, 1150, pp. 1181-1188. doi:10.1007/978-3-030-44038-1_108. google scholar
  • Küçüközmen, C.C. and Yüksel, A. (2006) ‘A Macroeconometric Model for Stress Testing Credit Portfolio’, in. 13th Annual Conference of the Multinational Finance Society, Edinburgh, p. 29. google scholar
  • Liu, Z. and Shi, Y. (2022) ‘A Hybrid IDS Using GA-Based Feature Selection Method and Random Forest,’ International Journal of Machine Learning and Computing, 12(2), p. 8. google scholar
  • Maimon, O. and Rokach, L. (eds) (2010) Data Mining and Knowledge Discovery Handbook. Boston, MA: Springer US. doi:10.1007/978-0-387-09823-4. google scholar
  • Marti, R., Pardalos, P.M. and Resende, M.G.C. (eds) (2018) Handbook of Heuristics. Cham: Springer International Publishing. doi:10.1007/978-3-319-07124-4. google scholar
  • Mohammadpour, J. et al. (2022) ‘Machine learning regression-CFD models for the nanofluid heat transfer of a microchannel heat sink with double synthetic jets,’ International Communications in Heat and Mass Transfer, 130, p. 105808. doi:10.1016/j.icheatmasstransfer.2021.105808. google scholar
  • Quinto, B. (2020) Next-Generation Machine Learning with Spark: Covers XGBoost, LightGBM, Spark NLP, Distributed Deep Learning with Keras, and More. Berkeley, CA: Apress. doi:10.1007/978-1-4842-5669-5. google scholar
  • Rajaleximi, P., Ahmed, M. and Alenezi, A. (2019) ‘Feature Selection using Optimized Multiple Rank Score Model for Credit Scoring,’ International Journal of Intelligent Engineering and Systems, 12(2), pp. 74-84. doi:10.22266/ijies2019.0430.08. google scholar
  • Ravisankar, P. et al. (2011) ‘Detection of Financial Statement Fraud and Feature Selection using Data Mining Techniques, Decision Support Systems, 50(2), pp. 491-500. doi:10.1016/j.dss.2010.11.006. google scholar
  • Sakthi Vel, S. (2021) ‘Pre-Processing Techniques of Text Mining using Computational Linguistics and Python Libraries,’ in 2021 International Conference on Artificial Intelligence and Smart Systems (ICAIS). 2021 International Conference on Artificial Intelligence and Smart Systems (ICAIS), Coimbatore, India: IEEE, pp. 879-884. doi:10.1109/ICAIS50930.2021.9395924. google scholar
  • Syukur, A. et al. (2018) ‘Bootstrapping and Weighted Information Gain in Support Vector Machine for Customer Loyalty Prediction,’ Journal of Internet Banking and Commerce, p. 1. google scholar
  • Tanuwijaya, J. and Masten, I. (2019) ‘LQ45 Stock Index Prediction using k-Nearest Neighbors Regression’, International Journal of Recent Technology and Engineering, 8(3), pp. 2388-2391. doi:10.35940/ijrte.C4663.098319. google scholar
  • Tepegöz, Ş.M. (2018) ‘FİNANSMAN ŞİRKETLERİNDE İÇ KONTROL YAPISI YÖNTEMİ’, Öneri Dergisi, 13(50), pp. 35-51. doi:10.14783/maruoneri.v13i38778.410464. google scholar
  • Vijayanand, R., Devaraj, D. and Kannapiran, B. (2018) ‘Intrusion Detection System for Wireless Mesh Network using Multiple Support Vector Machine Classifiers with Genetic-Algorithm-Based Feature Selection,’Computers & Security, 77, pp. 304-314. doi:10.1016/j.cose.2018.04.010. google scholar


Istanbul University Press aims to contribute to the dissemination of ever growing scientific knowledge through publication of high quality scientific journals and books in accordance with the international publishing standards and ethics. Istanbul University Press follows an open access, non-commercial, scholarly publishing.