Modeling the probability of default and calculation of the catastrophic loss in a financial institution in Colombia

Authors

DOI:

https://doi.org/10.17981/econcuc.42.2.2021.Econ.2

Keywords:

Probability of default, Logistic regression, Credit risk, Liquidity, Indebtedness, Global adjustment

Abstract

The expected loss in a financial institution is the amount of capital that would be lost as a result of the exposure that the debt has over time. This work focuses on modeling the probability of default for a loan portfolio under two study scenarios, one with a normal default level and the other with a restricted default level. A database belonging to a consumer loan portfolio is taken as a reference, with a sample of 5,000 obligations analyzed in the period from January to December 2019. The statistical method used is the logistic regression based on the financial variables of liquidity and indebtedness, plus a non-financial variable such as age. The results show a model with a global adjustment level greater than 85% in the two study scenarios, where the income variable is the one that has the most influence on the logistic regression model. Finally, the applicability of logistic regression as a statistical tool in the search for forecasting models is ratified, with which it is possible to reduce the expected loss in a loan portfolio without increasing risk exposure.

Downloads

Download data is not yet available.

Author Biographies

Armando Lenin Támara Ayús, Universidad EAFIT

EHe is an Economist from the University of Antioquia, a specialist in project design and evaluation from the Universidad del Norte, a master's degree in finance sciences from the EAFIT University and a PhD from the University of Medellín. His research interests include topics related to credit risk, business bankruptcy, and real options.

José Eduardo Segura Ramos, Politécnico de Colombia

He is an Economist from CECAR, a specialist in finance and a master's degree in financial administration from the EAFIT University. His research interests include topics related to credit risk and the probability of default.

Ignacio Emilio Chica Arrieta, Universidad de Córdoba

He is a Chemical Engineer from the University of Antioquia, a master's degree in administration from the EAFIT University. His research interests include management related topics.

References

Affes, Z. & Hentati, R. (2017). Predicting US Banks Bankruptcy: Logit Versus Canonical Discriminant Analysis. Computational Economics, (54), 199–244. https://doi.org/10.1007/s10614-017-9698-0

Alaka, H., Oyedele, L., Owolabi, H., Kumar, V., Ajayi, S., Akinade, O. & Bilal, M. (2018). Systematic Review of Bankruptcy Prediction Models: Towards A Framework for Tool Selection. Expert Systems With Applications, (94), 164–184. https://doi.org/10.1016/j.eswa.2017.10.040

Apilado, V., Warner, D. & Dauten, J. (1974). Evaluative Techniques in Consumer Finance-- Experimental Results and Policy Implications for Financial Institutions. The Journal Of Financial And Quantitative Analysis, 9(2), 275–283. https://doi.org/10.2307/2330105

Assef, F. & Steiner, M. (2020). Ten-year evolution on credit risk research: A systematic literature review approach and discussion. Ingenieria e Investigacion, 40(2), 1–21. https://doi.org/10.15446/ing.investig.v40n2.78649

Cappon, A., Gorenstein, A., Mignot, S. & Manuel, G. (2018). Credit ratings, default probabilities, and logarithms. Journal of Structured Finance, 24(1), 39–49. https://doi.org/10.3905/jsf.2018.24.1.039

Castro, D. y Soto, A. (2017). Estimación de la probabilidad de incumplimiento para las firmas del sector económico industrial y comercial en una entidad financiera colombiana entre los años 2009 y 2014. Cuadernos de Economía, 36(71), 293–319. https://doi.org/10.15446/ cuad.econ.v36n71.55273

Chen, N., Ribeiro, B. & Chen, A. (2016). Financial credit risk assessment: a recent review. Artificial Intelligence Review, 45(1), 1–23. https://doi.org/10.1007/s10462-015-9434-x

Davis, R., Edelman, D. & Gammerman, A. (1992). Machine learning algorithms for credit-card applications. IMA Journal of Management Mathematics, 4(1), 43–51. https://doi.org/10.1093/imaman/4.1.43

Dendramis, Y., Tzavalis, E. & Adraktas, G. (2018). Credit risk modelling under recessionary and financially distressed conditions. Journal of Banking and Finance, 91, 160–175. https://doi.org/10.1016/j.jbankfin.2017.03.020

Do Prado, J., Carvalho, F., Benedicto, G. y Lima, A. (2019). Análisis del riesgo de crédito que enfrentan las empresas de capital abierto en Brasil: un enfoque utilizando análisis discriminante regresión logística y redes neuronales artificiales. Estudios Gerenciales, 35(153), 347–360. https://doi.org/10.18046/j.estger.2019.153.3151

Durovic, A. (2017). Estimating probability of default on peer to peer market – Survival analysis approach. Journal of Central Banking Theory and Practice, 62(2), 149–167. https://doi.org/10.1515/jcbtp-2017-0017

Fantazzini, D. & Zimin, S. (2020). A multivariate approach for the simultaneous modelling of market risk and credit risk for cryptocurrencies. Journal of Industrial and Business Economics, 47(1), 19–69. https://doi.org/10.1007/s40812-019-00136-8

Grundke, P., Pliszka, K. & Tuchscherer, M. (2019). Model and estimation risk in credit risk stress tests. Review of Quantitative Finance and Accounting, 55, 163–199. https://doi.org/10.1007/s11156-019-00840-5

Imtiaz, S. & Brimicombe, A. (2017). A Better Comparison Summary of Credit Scoring Classification. International Journal of Advanced Computer Science and Applications, 8(7), 1–4. https://doi.org/10.14569/IJACSA.2017.080701

Lane, S. (1972). Submarginal Credit Risk Classification. The Journal Of Financial And Quantitative Analysis, 7(1), 1379–1385. https://doi.org/10.2307/2330069

Lohmann, C. & Ohliger, T. (2018). Nonlinear relationships in a logistic model of default for a high-default installment portfolio. Journal of Credit Risk, 14(1), 45–68. https://doi.org/10.21314/JCR.2017.232

Myers, J. & Forgy, E. (1963). The Development of Numerical Credit Evaluation Systems. Journal Of The American Statistical Association, 58(303), 799–806. https://doi.org/10.2307/2282727

RiskSimulator. (2020). [Sofware]. Available from www.software-shop.com/producto/risk-simulator

Russo, V., Lagasio, V., Brogi, M. & Fabozzi, F. (2020). Application of the Merton model to estimate the probability of breaching the capital requirements under Basel III rules. Annals of Finance, 16(1), 141–157. https://doi.org/10.1007/s10436-020-00358-0

Sariev, E. & Germano, G. (2020). Bayesian regularized artificial neural networks for the estimation of the probability of default. Quantitative Finance, 20(2), 311–328. https://doi.org/10.1080/14697688.2019.1633014

Song, S., Wang, Y. & Xu, G. (2020). On the probability of default in a market with price clustering and jump risk. Mathematics and Financial Economics, 14(2), 225–247. https://doi.org/10.1007/s11579-019-00253-x

Srinivasan, V. & Kim, Y. (1987). Credit Granting: A Comparative Analysis of Classification Procedures. The Journal Of Finance, 42(3), 665–681. https://doi.org/10.2307/2328378

SPSS. (versión 24). Statistical Package for the Social Sciences. [Sofware]. Armonk: IBM. Disponible en https://www.ibm.com/support/pages/downloading-ibm-spssstatistics-24

Superfinanciera. (2002). . Circular externa 011. Bogotá, D.C.: Superfinanciera. Disponible en http://legal.legis.com.co/document/Index?obra=legcol&document=legcol_75992041c75992048a75992043f75992034e75990430a75010151f75992034

Támara, A., Villegas, G. y De Andrés, J. (2019). Una revisión sistemática de la literatura en torno a la quiebra empresarial para el período 2012-2017. Espacios, 40(4). Disponible en http://www.revistaespacios.com/a19v40n04/a19v40n04p25.pdf

Támara, A., Villegas, G., Leones, M. y Salazar, J. (2018). Modelación del riesgo de insolvencia en empresas del sector salud empleando modelos logit. Revista de métodos cuantitativos para la economía y la empresa,, 26, 128–145. Disponible en https://www.upo.es/revistas/index.php/RevMetCuant/article/view/2757

Trejo, J., Martínez, M. & Venegas, F. (2017). Credit risk management at retail in Mexico: An econometric improvement in the selection of variables and changes in their characteristics. Contaduría y Administración, 62(2), 399–418. https://doi.org/10.1016/j.cya.2017.02.006

Tsai, C. & Hung, C. (2014). Modeling credit scoring using neural network ensembles. Kybernetes, 43(7), 1114–1123. https://doi.org/10.1108/k-01-2014-0016

Van Thiel, D. & Van Raaij, W. (2019). Artificial intelligence credit risk prediction: An empirical study of analytical artificial intelligence tools for credit risk prediction in a digital era. Journal of Risk Management in Financial Institutions, 12(3), 268–286. https://doi.org/10.33423/jaf.v19i8.2622

Wiginton, J. (1980). A note on the comparison of logit and discriminant models of consumer credit behaviour. Journal of Financial and Quantitative Analysis, 15(3), 757–770. https://doi.org/10.2307/2330408

Downloads

Published

2021-03-15

How to Cite

Támara Ayús, A. L., Segura Ramos, J. E., & Chica Arrieta, I. E. (2021). Modeling the probability of default and calculation of the catastrophic loss in a financial institution in Colombia. ECONÓMICAS CUC, 42(2), 173–186. https://doi.org/10.17981/econcuc.42.2.2021.Econ.2

Issue

Vol. 42 No. 2 (2021)

Section

Articles: Economy and Finance

License

Copyright (c) 2021 ECONÓMICAS CUC

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

You are free to:

  1. Share — copy and redistribute the material in any medium or format
  2. The licensor cannot revoke these freedoms as long as you follow the license terms.

Under the following terms:

  1. Attribution — You must give appropriate credit , provide a link to the license, and indicate if changes were made . You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
  2. NonCommercial — You may not use the material for commercial purposes .
  3. NoDerivatives — If you remix, transform, or build upon the material, you may not distribute the modified material.
  4. No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.

Most read articles by the same author(s)