Estimating credit default probabilities using stochastic optimisation

Dominic Joseph; Dominic Joseph

doi:10.3934/DSFE.2021014

Data Science in Finance and Economics

2021, Volume 1, Issue 3: 253-271. doi: 10.3934/DSFE.2021014

Previous Article Next Article

Research article Special Issues

Estimating credit default probabilities using stochastic optimisation

Dominic Joseph ^,

Independent researcher, Kerala, India

Received: 20 October 2021 Accepted: 15 November 2021 Published: 19 November 2021
JEL Codes: C02, C15, C61, C63, G32

Banks and financial institutions all over the world manage portfolios containing tens of thousands of customers. Not all customers are high credit-worthy, and many possess varying degrees of risk to the Bank or financial institutions that lend money to these customers. Hence assessment of default risk that is calibrated and reflective of actual credit risk is paramount in the field of credit risk management. This paper provides a detailed mathematical framework using the concepts of Binomial distribution and stochastic optimisation, in order to estimate the Probability of Default for credit ratings. The empirical results obtained from the study have been illustrated to have potential application value and perform better compared to other estimation models currently in practise.
- credit risk,
- default rate,
- probability of default,
- calibration,
- stochastic optimization
Citation: Dominic Joseph. Estimating credit default probabilities using stochastic optimisation[J]. Data Science in Finance and Economics, 2021, 1(3): 253-271. doi: 10.3934/DSFE.2021014

Related Papers:

Abstract

Banks and financial institutions all over the world manage portfolios containing tens of thousands of customers. Not all customers are high credit-worthy, and many possess varying degrees of risk to the Bank or financial institutions that lend money to these customers. Hence assessment of default risk that is calibrated and reflective of actual credit risk is paramount in the field of credit risk management. This paper provides a detailed mathematical framework using the concepts of Binomial distribution and stochastic optimisation, in order to estimate the Probability of Default for credit ratings. The empirical results obtained from the study have been illustrated to have potential application value and perform better compared to other estimation models currently in practise.

References

[1]	Basel Committee on Banking Supervision (2001) The Internal Ratings-Based Approach Consultative Document. Available from: https://www.bis.org/publ/bcbsca05.pdf.
[2]	Chang YP, Yu CT (2014) Bayesian confidence intervals for probability of default and asset correlation of portfolio credit risk. Comput Stat 29: 331–361. doi: 10.1007/s00180-013-0453-2
[3]	Clifford T, Marianski A, Sebesteyn K (2013) Low default portfolio modelling: Probability of default calibration conundrum. In Credit Scoring and Credit Control XⅢ Conference.
[4]	Dwyer DW (2007) The distribution of defaults and bayesian model validation. J Risk Model Valid 1: 23–53. doi: 10.21314/JRMV.2007.003
[5]	Erlenmaier U (2011) The shadow rating approach: Experience from banking practice. The Basel Ⅱ Risk Parameters, Springer, 37–74.
[6]	Fernandes G, Rocha CA (2011) Low default modelling: A comparison of techniques based on a real Brazilian corporate portfolio. In Credit Scoring and Credit Control ⅩⅢ Conference, 24–26.
[7]	Homaifar A, Qi CX, Lai SH (1994) Constrained optimization via genetic algorithms. Simulation 62: 242–254. doi: 10.1177/003754979406200405
[8]	Kiefer NM (2009) Default estimation for low-default portfolios. J Empir Financ 16: 164–173. doi: 10.1016/j.jempfin.2008.03.004
[9]	Kiefer NM (2010) Default estimation and expert information. J Bus Econ Stat 28: 320–328. doi: 10.1198/jbes.2009.07236
[10]	Kirkpatrick S, Gelatt CD, Vecchi MP (1983) Optimization by Simulated Annealing. Science 220: 671–680. doi: 10.1126/science.220.4598.671
[11]	Krahnen JP, Weber M (2001) Generally accepted rating principles: A primer. J Bank Financ 25: 3–23. doi: 10.1016/S0378-4266(00)00115-1
[12]	Kruger M (2015) Validation and monitoring of pd models for low default portfolios using proc mcmc. In SAS Global Forum 2015.
[13]	Pluto K, Tasche D (2005) Thinking Positively. Risk, 72–78.
[14]	S&P (2021) Default, Transition, and Recovery: 2020 Annual Global Corporate Default And Rating Transition Study. Available from: https://www.maalot.co.il/Publications/TS20210408160139.PDF.
[15]	Surzhko D (2017) Bayesian Approach to PD Calibration and Stress-testing in Low Default Portfolios. J Appl Financ Bank 7: 1–6.
[16]	Tasche D (2002) Remarks on the monotonicity of default probabilities. Available from: https://arXiv.org/pdf/cond-mat/0207555.pdf.
[17]	Tasche D (2009) Estimating discriminatory power and PD curves when the number of defaults is small. Working paper, Lloyds Banking Group.
[18]	Tasche D (2013) Bayesian estimation of probabilities of default for low default portfolios. J Risk Manage Financ Inst 6: 302–326.
[19]	Tasche D (2013) The art of probability-of-default curve calibration. J Credit Risk 9: 63–103. doi: 10.21314/JCR.2013.169
[20]	Van der Burgt M (2008) Calibrating low-default portfolios, using the cumulative accuracy profile. J Risk Model Valid 1:17–33. doi: 10.21314/JRMV.2008.016
[21]	Yeniay Ö (2005) Penalty function methods for constrained optimization with genetic algorithms. Math Comput Appl 10: 45–56.

DSFE-01-03-014-s001.pdf

Reader Comments

Your name:*

Email:*
© 2021 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)