Backtesting analysis. How to assess the quality of PD models in a retail banking

• Authors: Siarka Paweł

Title variants

PL

Analiza backtesting. Jak ocenić jakość modeli PD w bankowości detalicznej

• Languages of publication: EN

Abstracts

EN

The paper refers to the probability of default model validation procedure in retail banking. The author presents the idea of backtesting analysis focusing on sensitivity analysis of capital requirements under stress scenarios. The paper addresses statistical methods which can be applied in credit risk management under the backtesting exercise in retail banking. The advantages and drawbacks of specific approaches are discussed. Furthermore, the outcomes of the empirical implementation of selected methods are presented. The author considers the impact of positive asset correlation on various validation approaches, where no correlation is assumed, and proves that the zero-correlation assumptions may result in a more prudent approach. This finding was confirmed by the empirical analysis performed for retail portfolios. The research concerned PD parameters calculated for car and mortgage loans. The backtesting results revealed that PD forecasts created for mortgage portfolios underestimated credit risk during the crisis period which started in 2008. However, car loan portfolio credit risk predictions appeared to be robust.

PL

W niniejszym artykule odniesiono się do zagadnienia weryfikacji jakości modeli służących do szacowania prawdopodobieństwa niewypłacalności w bankowości detalicznej. Autor przedstawił koncepcję analizy backtesting w świetle wrażliwości wymogów kapitałowych w odniesieniu do testowania warunków skrajnych. W artykule odniesiono się do zagadnienia weryfikacji jakości prognoz modeli służących do szacowania prawdopodobieństwa niewypłacalności. Przedstawiono i omówiono wyniki wybranych metod. Autor omówił również wpływ dodatniej korelacji aktywów na uzyskane wyniki. Wykazał, że założenie zerowej korelacji może skutkować bardziej konserwatywnymi wynikami. Ustalenie to potwierdzono przez analizę empiryczną przeprowadzoną dla portfeli detalicznych. Badanie dotyczyło parametrów PD szacowanych dla portfeli kredytów samochodowych oraz hipotecznych. Otrzymane wyniki wykazały, że prognozy PD opracowane dla portfela kredytów hipotecznych niedoszacowują ryzyko kredytowe. Prognozy ryzyka kredytowego dla portfela kredytów samochodowych okazały się trafne.

Keywords

EN

backtesting; model validation; probability of default

PL

ryzyko kredytowe; prawdopodobieństwo niewypłacalności; PD

• Publisher: Wydawnictwo Uniwersytetu Ekonomicznego we Wrocławiu
• Journal: Prace Naukowe Uniwersytetu Ekonomicznego we Wrocławiu
• Year: 2019
• Issue: vol. 63, nr 8
• Pages: 230-244

Contributors

author

Siarka Paweł

References

• Basel Committee on Banking Supervision, 1988, International Convergence of Capital Measurement and Capital Standards, Basel.
• Basel Committee on Banking Supervision (BCBS), 2006, International Convergence on Capital Measurement and Capital Standards, Bank for International Settlements, Basel.
• Blochwitz S., Hohl S., Tasche D., Wehn C.S., 2004, Validating Default Probabilities on Short Time Series, Deutsche Bundesbank, Working Paper.
• Blochwitz S., Hohl S., Tasche D., Wehn C.S., 2005, Reconsidering Ratings, Deutsche Bundesbank, Working Paper, May.
• Braun A., Rymaszewki P., Schmieser H., 2010, A Traffic Light Approach to Solvency Measurement of Swiss Occupational Pension Funds, Working Papers on Risk Management and Insurance, no. 74, University of St. Gallen.
• Coppens F., Gonzalez F., Winkler G., 2007, The Performance of Credit Ratings Systems in the Assessment of Collateral Used in Eurosystem Monetary Policy Operations, Occasional Paper Series, European Central Bank.
• Crook J., Bellotti T., 2009, Asset Correlations for Credit Card Defaults, Working Paper, Credit Research Centre, University of Edinburgh.
• Düllmann K., Scheicher M., Schmieder C., 2007, Asset Correlations and Credit Portfolio Risk − An Empirical Analysis, Deutsche Bundesbank Discussion Paper, series 2, no. 13.
• Emmer S., Tasche D., 2005, Calculating Credit Risk Capital Charges with the One-Factor Model, http://arxiv.org/abs/cond-mat/0302402v5.
• Engelman B., 2006, The Basel II Risk Parameters: Estimation, Validation, and Stress Testing, Springer.
• Ferguson T.S., 1967, Mathematical Statistics. A Decision Theoretic Approach, Academic Press, London.
• Hamerle A., Liebig T., Scheule H., 2004, Forecasting Credit Portfolio Risk, Deutsche Bundesbank, Working Paper, May.
• IASB, 2014, IFRS Standard 9: Financial Instruments.
• Jackson P., Perraudin W., 2000, Regulatory implications of credit risk modelling, Journal of Banking & Finance, 24.
• Jajuga K., 1993, Multivariate Statistical Analysis, PWN, Warszawa.
• Kupiec N.H., 1995, Techniques for verifying the accuracy of risk measurement models, Journal of Derivatives, 3, pp. 73-84.
• Lopez J.A., 2004, The empirical relationship between average asset correlation, firm probability of default, and asset size, Journal of Financial Intermediation, 13, pp. 265-283.
• Merton R.C., 1974, On the pricing of corporate debt: The risk structure of interest rates, Journal of Finance, 29, pp. 449-470.
• Pluto K., Tasche D., 2005, Thinking positively, Risk, 18(8), pp. 72-78.
• Rösch D., Scheule H., 2004, Forecasting retail portfolio credit risk, Journal of Risk Finance, Winter/Spring, pp. 16-32.
• Schuermann T., Hanson S., 2004, Estimating Probability of Default, Federal Reserve Bank of New York Staff Reports.
• Siarka P., 2012, Assets Correlation. The Issue of Estimating the Losses on the Example of Mortgage Portfolio, Bank & Credit, National Bank of Poland, Warsaw.
• Siarka P., 2014, Asset correlation of retail loans in the context of the New Basel Capital Accord, The Journal of Credit Risk, 10 (3)
• Siarka P., Chan L., 2015, Comprehensive capital analysis and review stress tests: Is regression the only tool for loss projection?, Journal of Risk Model Validation, 9 (3), pp. 71-99.
• Svec M., 2009, PD Backtesting Empirycal Study on Credit Retail Portfolio, CSOB Bank.
• Tasche D., 2003, A Traffic Lights Approach to PD Validation, Deutsche Bundesbank, Working Paper.
• Tasche D., Pluto K., 2005, Estimating Probabilities of Default for Low Default Portfolios, Working Paper, https://papers.ssrn.com/sol3/papers.cfm?abstract_id=635301.
• Vasicek O., 1991, Working Paper, KMV Corporation.
• Vasicek O., 2002, The Distribution of Loan Portfolio Value, Risk.