Abstract
This paper proposes an approach to decompose the RR/LGD model development process with two stages, specifically, for the RR/LGD rating model, and to calibrate the model using a linear form that minimizes residual risk. The residual risk in the recovery of defaulted debts is determined by the high uncertainty of the recovery level according to its average expected level. Such residual risk should be considered in the capital requirements for unexpected losses in the loan portfolio. This paper considers a simple residual risk model defined by one parameter. By developing an optimal RR/LGD model, it is proposed to use a residual risk metric. This metric gives the final formula for calibrating the LGD model, which is proposed for the linear model. Residual risk parameters are calculated for RR/LGD models for several open data sources for developed and developing markets. An implied method for updating the RR/LGD model is constructed with a correction for incomplete recovery through the recovery curve, which is built on the training sets. Based on the recovery curve, a recovery indicator is proposed which is useful for monitoring and collecting payments. The given recommendations are important for validating the parameters of RR/LGD model.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
According to the definition given, for example, by the Bank of Russia (see Bank of Russia Ordinance No. 3624-U, dated April 15, 2015, “On Requirements for the Risk and Capital Management System of a Credit Organization and Banking Group”), residual risk is the risk remaining after the Bank’s actions to reduce inherent risk. Suppose a bank takes measures (that is, requires collateral) to recover debt after default, based on which it statistically fairly expects a recovery share of RR = 1-LGD. And, let’s say, on a statistically significant portfolio, this share of recovery will take place. However, due to the dispersion of LGD and the granularity of the default part of the portfolio, deviations from the expected value will be observed, including towards losses. This gives unexpected losses related to residual risk.
- 2.
A model-homogeneous population should be understood, for example, such industry segments of borrowers as “Banks”, “Individuals, consumer loans”, “Mass segment of small business”, “Large corporate business” including credited to a particular bank, etc. It is reasonable to classify LGD segments of credit assets by business model or financial instrument. For each segment, various parameters γ are possible.
- 3.
LGD rating means any specially developed function that depends on the risk-dominant parameters of LGD/RR, which correlates with the implemented LGD/RR.
- 4.
The mean is in the sense of RRavg according to the app. A.2.
- 5.
MSE—Mean Square Error.
- 6.
A normal distribution of the random parameter ξ can be described using the substitution for F (ξ), where F is the distribution function of ξ.
References
Allen, L. Saunders, A. (2005). A Survey of Cyclical Effects in Credit Risk Measurement Models. https://papers.ssrn.com/sol3/papers.cfm?abstract_id=315561
Antonova, B. N. (2012). Ocenka stavki vosstanovleniya po rossijskim korporativnym obligaciyam. Journal of Corporate Finance Research, 6(4), 130–143. [in Russian].
Araten, M., Jacobs, M., & Varshney, P. (2004). Measuring LGD on commercial loans: An 18-year internal study. RMA Journal, 86(8), 96–103.
Basel II. (2006). International convergence of capital measurement and capital standards: a revised framework - comprehensive version. Part 2. pp. 295. https://www.bis.org/publ/bcbs128b.pdf
Basel III. (2011). A global regulatory framework for more resilient banks and banking systems. Part 1, pp. 139. https://www.bis.org/publ/bcbs189.pdf
Benjelloun, М. (2019). Stochastic modelling of the loss given default (LGD) for non-defaulted assets. This work was supported by the Global Research & Analytics Dept. of Chappuis Halder & Co. https://www.chappuishalder.com/wp-ontent/uploads/2019/03/GRA_White_Paper_LGD_stochastic.pdf
Bonini, S., & Caivano, G. (2014). Development of a LGD model basel2 compliant: A case study. In Mathematical and Statistical Methods for Actuarial Sciences and Finance, 2014 (pp. 45–48). Springer. https://doi.org/10.1007/978-3-319-05014-0_10. ISBN: 3319050141.
Bonini, S., & Caivano, G. (2016). Econometric approach for Basel II Loss Given Default Estimation: From discount rate to final multivariate model. White paper. https://www.semanticscholar.org/paper/Econometric-approach-for-Basel-II-Loss-Given-%3A-from/fc954a9ac25c2fd9f2de67b9f89b53aa36742e6c
Cohen, M., Nelson, R., & Walsh, P. (2002). Links and impacts: The influence of public research on industrial R&D. Management Science, 48(1), 1–23.
CreditMetrics. (1997). Technical Document. JP Morgan.
Dermine, J., & de Carvalho, C. N. (2006). Bank loan losses-given-default: A case study. Journal of Banking and Finance, 30(4), 1219–1243.
Ermolova, M. D., & Penikas, H. I. (2017). PD-LGD correlation study: Evidence from the Russian corporate bond market. Model Assisted Statistics and Applications, 12(4), 335–358.
Felsovalyi, A., & Hurt, L. (1998). Measuring loss on Latin American defaulted bank loans: A 27-year study of 27 countries. Journal of Lending and Credit Risk Management, 80, 41–46.
Frye, J., & Jacobs, M., Jr. (2012). Credit loss and systematic loss given default. The Journal of Credit Risk, 8(1), 109–140.
Gordy, M. B., & Lutkebohmert, E. (2013). Granularity adjustment for regulatory capital assessment. International Journal ofCentral Banking, 9(3), 38–77.
Grunert, J., & Weber, M. (2009). Recovery rates of commercial lending: Empirical evidence for German companies. Journal of Banking & Finance, Elsevier, 33(3), 505–513. https://doi.org/10.1016/j.jbankfin.2008.09.002.
Jankowitscha, R., Naglerb, F., & Subrahmanyam, M. G. (2014). The determinants of recovery rates in the US corporate bond market. Journal of Financial Economics., 114(1), 155–177. https://doi.org/10.1016/j.jfineco.2014.06.001.
Karminsky, A. M., Lozinskaia, A. M., & Ozhegov, E. M. (2016). Estimation methods of creditor’s loss in residential mortgage lending. HSE Economic Journal, 20(1), 9–51. [in Russian].
Košak, M., & Poljšak, J (2010). Loss given default determinants in a commercial bank lending: an emerging market case study. Zbornik radova Ekonomskog Fakulteta u Rijeci: časopis za ekonomsku teoriju i praksu. - Rijeka, ISSN 0353-3689, ZDB-ID 12830379. - 28.2010, 1, p. 61–88.
Loterman, G., Brown, I., Martens, D., Mues, C., & Baesens, B. (2012). Benchmarking regression algorithms for loss given default modeling. International Journal of Forecasting, 28, 161–170.
Miu, P., & Ozdemir, B. (2006). Basel requirement of downturn LGD: Modeling and estimating PD & LGD correlations. Journal of Credit Risk, 2(2), 43–68.
Moody’s Corporation. (2017). Annual Default Study: Corporate Default and Recovery Rates, 1920–2016 - Excel data.
Qi, M., & Yang, X. (2009). Loss given default of high loan-to-value residential Mortgages. Journal of Banking and Finance, 33(5), 788–799.
Qi, M., & Zhao, X. (2011). Comparison of modeling methods for loss given default. Journal of Banking and Finance, 35(11), 2842–2855.
Schuermann, T. (2004). What do we know about loss given default? (February 2004). Wharton Financial Institutions Center Working Paper No. 04-01. Available at SSRN: https://doi.org/10.2139/ssrn.525702
Seidler, J., Konečný, T., Belyaeva, A., Belyaev, K. (2017). The time dimension of the links between loss given default and the macroeconomy. Working Paper Series 2037, European Central Bank. https://www.ecb.europa.eu/pub/pdf/scpwps/ecbwp2037.en.pdf
Strutz, T. (2016). Data Fitting and Uncertainty (A practical introduction to weighted least squares and beyond). Springer Vieweg. ISBN 978-3-658-11455-8., paper 3.
Vasicek, O. (1987). Probability of Loss on a Loan Portfolio. [on-line], San Francisco, KMV, c1987, [cit. 27th March, 2009]. http://www.moodyskmv.com/research/files/wp/Probability_of_Loss
Vujnović, M., Nikolić, N., & Vujnović, A. (2016). Validation of loss given default for corporate. Journal of Applied Engineering Science, 14(4), 465–476. https://doi.org/10.5937/jaes14-11752.
Witzany, J. (2009). Unexpected recovery risk and LGD discount rate determination. European Financial and Accounting Journal, ISSN 1805-4846, University of Economics, Faculty of Finance and Accounting Prague, 4(1), 61–84. https://doi.org/10.18267/j.efaj.63.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
The Estimation Procedure of the Calculated Standard Error for the Average Marginal Share of Repayment
The Estimation Procedure of the Calculated Standard Error for the Average Marginal Share of Repayment
The solution of problem (5) gives the optimal values of the recovery period T and the limiting recovery R∞. The error of the values depends on the quality statistics of the approximation of the cumulative recovery of the recovery curve (4). The linear problem of the parameter estimation question θ = {R, T} for the non-linear regression problem (τ) = ρτ(θ) + δτ ∙ ετ , near the optimal solution θ of problem (5) is given a linear regression relation for the error Δθ = θ − θ in the standardized form:
where ∂θρτ is composed by the n × 2 partial derivatives matrix \( \left[\frac{\partial\ }{\partial R}{\rho}_{\tau}\left(R,T\right),\frac{\partial\ }{\partial T}{\rho}_{\tau}\left(R,T\right)\right],{\varepsilon}_{\tau } \) assumed to be normal uncorrelated random variable with unknown variance for each recovery period τ , of which there are n. Apparently, for an optimal solution in the sense of equation (5) for θ, the solution of problem (A1) for Δθ will be obvious Δθ = 0. However, the error Δθ will be expressed through the covariance matrix according to the well-known formula (see, for example, Strutz 2016):
where for (A1):
Denoting the partial derivatives as:
and according for the estimation error R, the only the upper diagonal element of the matrix cov(Δθ), it is needed to obtain
To estimate the error R∞ as the measure for the standard deviation δR∞, it is necessary in formula (45) to substitute the solution of problem (5) as R—the limiting recovery R∞, the time for recovery T, and δτ2 = δRRAvg2(τ) or δRRw2(τ), these replacements depend on the calculation of the recovery curve.
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Pomazanov, M. (2021). Loss Given Default Estimations in Emerging Capital Markets. In: Karminsky, A.M., Mistrulli, P.E., Stolbov, M.I., Shi, Y. (eds) Risk Assessment and Financial Regulation in Emerging Markets' Banking. Advanced Studies in Emerging Markets Finance. Springer, Cham. https://doi.org/10.1007/978-3-030-69748-8_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-69748-8_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-69747-1
Online ISBN: 978-3-030-69748-8
eBook Packages: Economics and FinanceEconomics and Finance (R0)