Stezhkin A.A.Moscow Institute of Physics and Technology (State University), Dolgoprudny, Moscow Oblast, Russian Federation alex79216@mail.ru
Importance To assess credit risks more accurately as part of Basel II recommendations of the Basel Committee on Banking Supervision, there is the Internal Ratings-Based (IRB) approach. Considering its specifics, it's worth mentioning an importance of evaluating the adequacy of elaborated models, or validation as it is denoted in the Russian practice, in addition to the process of setting up a model that requires complicated mathematical models and approaches. Objectives The research aims at the high level review of validating rating systems, investigating separate components of the validation process, analyzing and adapting mathematical approaches to validation, and performing a comparative analysis of alternative approaches and examining international experience. Methods The apparatus of mathematical, probabilistic and statistical analysis is used in the research to verify whether the rating model of the credit institutions complies with each concept of validation (discriminative power, calibration, stability). I conduct an empirical analysis of existing global practices, theoretical and practical researches and overviews. Results Standardized methods of mathematical and statistical analysis were adapted for specific purposes of validation. I conducted a comparative analysis of alternatives and gave my own recommendations on their practical applications. The research systematized international experience in examining validation approaches in terms of approximate quantitative criteria of applicability. Conclusions and Relevance I conclude that methods of mathematical and statistical analysis are respectively efficient for validation of rating systems. The relevant regulators are reasonable to prudently stipulate and set forth minimum standards of validating credit institutions' rating systems.
Greene W. Econometric Analysis. Prentice Hall International, 2003, 802 p.
Wooldridge J. Econometric Analysis of Cross Section and Panel Data. Cambridge, MIT Press, 2002, 735 p.
Maarse B. Backtesting Framework for PD, EAD and LGD. Rabobank, 2012, 85 p.
Higgins J.J. Introduction to Modern Nonparametric Statistics. Kansas State University, 2004, pp. 29–34.
Siddiqi N. Credit Risk Scorecards: Developing and Implementing Intelligent Credit Scoring. Hoboken, NJ, John Wiley & Sons, Inc., 2006, 208 p.
International Convergence of Capital Measurement and Capital Standards. A Revised Framework. Bank for International Settlements, 2006, 347 p.
Supervisory Statement. Credit Risk: Internal Ratings Based Approaches. Bank of England, Prudential Regulation Authority, 2013, 23 p.
Wu X. Credit Scoring Model Validation. University of Amsterdam, 2008, 58 p.
Christodoulakis G., Satchell S. The Analytics of Risk Model Validation. Elsevier, 2008, 217 p.
Future of the IRB Approach. European Banking Authority, Discussion Paper, March 4, 2015, 60 p.
Hastie T., Tibshirani R., Friedman J. The Elements of Statistical Learning. Springer, 2008, 758 p.
Nickell P., Perraudin W., Varotto S. Stability of Ratings Transitions. Bank of England, Working Paper, 2001, 72 p.
Castermans G., Martens D., van Gestel T., Hamers B., Baesens B. An Overview and Framework for PD Backtesting and Benchmarking. Journal of the Operational Research Society, 2010, vol. 61, iss. 3, pp. 359–373.
Studies on the Validation of Internal Rating Systems. Bank for International Settlements. Working Paper, 2005, no. 14, 120 p.
Blochwitz S., Hamerle A., Hohl S., Rauhmeir R., Rösch D. Myth and Reality of Discriminatory Power for Rating Systems. Wilmott Magazine, 2005, pp. 2–6.
Engelmann B., Hayden E., Tasche D. Testing Rating Accuracy. Risk, 2003, no. 16, pp. 82–86.
Hull J.C. Risk Management and Financial Institutions. Prentice Hall International, 2007, 502 p.
Li D., Bhariok R., Keenan S., Santilli S. Validation Techniques and Performance Metrics for Loss Given Default Models. The Journal of Risk Model Validation, 2009, no. 3, pp. 3–26.
Mui P., Ozdemir B. Practical and Theoretical Challenges in Validating Basel Parameters: Key Learnings from the Experience of a Canadian Bank. Journal of Credit Risk, 2005, no. 1(4), pp. 89–136.
Guidelines on Credit Risk Management, Rating Models and Validation. Vienna, Oesterreichische Nationalbank, 2004, 71 p.
Tasche D. Validation of Internal Rating Systems and PD Estimates. In: The Analytics of Risk Model Valuation. Elsevier, 2008, pp. 171–198.
