Christoph Siebenbrunner
ABSTRACT
Current financial regulation allows banks to use internal models for determining their risk-based capital requirements. Economic theory suggests that banks have incentives to report downward-biased risk weights, a problem that regulators aim to address by auditing banks' models. We study whether different audit standards by different regulators affect internal risk weights, indicating that banks subject to laxer standards may report too low risk weights. We present a supervised learning method to study this question that accounts for the fact that risk weights for the same portfolio could vary across banks even if there was no misreporting. Our approach is based on a generalized least squares technique that learns an individual model for each bank, which we combine with Group Lasso shrinkage to study the importance of different features. We analyze a large sample of internal risk weights for European banks. Our results show that regulator characteristics do have an economically significant impact on risk weights and that their importance is similar to that of relevant economic variables. We conclude that this provides empirical support for the claim that banks do indeed report biased risk weights, thereby undermining regulations aimed at preventing another financial crisis.
- M. Ahn. 2010. Random Effect Selection in Linear Mixed Models. Ph.D. Dissertation. North Carolina State University.Google Scholar
- Mihye Ahn, Hao Helen Zhang, and Wenbin Lu. 2012. Moment-based method for random effects selection in linear mixed models. Statistica Sinica 22, 4 (2012), 1539.Google ScholarCross Ref
- Douglas Bates, Martin Mächler, Ben Bolker, and Steve Walker. 2014. Fitting linear mixed-effects models using lme4. arXiv preprint arXiv:1406.5823 (2014).Google Scholar
- M. Behn, R. Haselmann, and V. Vig. 2016. The Limits of Model-based Regulation. Technical Report 1928. ECB. Working Paper Series.Google Scholar
- Andrea Beltratti and Giovanna Paladino. 2016. Basel II and regulatory arbitrage. Evidence from financial crises. Journal of Empirical Finance 39 (2016), 180--196.Google ScholarCross Ref
- Tobias Berg and Philipp Koziol. 2017. An analysis of the consistency of banks' internal ratings. Journal of Banking and Finance 78 (2017), 27--41.Google ScholarCross Ref
- Patrick Breheny and Jian Huang. 2015. Group descent algorithms for nonconvex penalized linear and logistic regression models with grouped predictors. Statistics and computing 25, 2 (2015), 173--187.Google Scholar
- Sophia Doeme and Stefan Kerbl. 2017. Comparability of Basel risk weights in the EU banking sector. Financial Stability Report 34 (2017), 68--89. https://EconPapers.repec.org/RePEc:onb:oenbfs:y:2017:i:34:b:2Google Scholar
- EBA. 2014. Results of 2014 EU-wide stress test. European Banking Authority (2014). https://www.eba.europa.eu/-/eba-publishes-2014-eu-wide-stress-test-resultsGoogle Scholar
- EBA. 2015. EU-wide Transparency Exercise 2013. European Banking Authority (2015). https://www.eba.europa.eu/risk-analysis-and-data/eu-wide-transparency-exercise/2015/resultsGoogle Scholar
- EBA. 2016. EU wide Stress Test Methodological Note. European Banking Authority (2016).Google Scholar
- EBA. 2017. EU-wide Transparency Exercise 2017. European Banking Authority (2017). https://www.eba.europa.eu/risk-analysis-and-data/eu-wide-transparency-exercise/2017Google Scholar
- EBA. 2018. EU-wide Transparency Exercise 2018. European Banking Authority (2018). https://www.eba.europa.eu/risk-analysis-and-data/eu-wide-transparency-exercise/2018Google Scholar
- EBA. 2019. EU-wide Transparency Exercise 2019. European Banking Authority (2019). https://www.eba.europa.eu/risk-analysis-and-data/eu-wide-transparency-exercise/2019Google Scholar
- EBA. 2020. RISK ASSESSMENT OF THE EUROPEAN BANKING SYSTEM. European Banking Authority (2020).Google Scholar
- Giovanni Ferri and Valerio Pesic. 2017. Bank regulatory arbitrage via risk weighted assets dispersion. Journal of Financial Stability 33 (2017), 331--345.Google ScholarCross Ref
- Jerome Friedman, Trevor Hastie, Robert Tibshirani, et al. 2001. The elements of statistical learning. Vol. 1. Springer series in statistics New York.Google Scholar
- David A Harville. 1974. Bayesian inference for variance components using only error contrasts. Biometrika 61, 2 (1974), 383--385.Google ScholarCross Ref
- Nicholas J Higham. 1997. Stable iterations for the matrix square root. Technical Report. 227--242 pages.Google Scholar
- Björn Imbierowicz, Axel Löffler, and Ursula Vogel. 2021. The transmission of bank capital requirements and monetary policy to bank lending in Germany. Review of International Economics 29, 1 (2021), 144--164.Google ScholarCross Ref
- Robert A Jarrow. 2009. Credit risk models. Annu. Rev. Financ. Econ. 1, 1 (2009), 37--68.Google Scholar
- Christoffer Kok, Carola Müller, Cosimo Pancaro, et al. 2019. The disciplining effect of supervisory scrutiny on banks' risk-taking: evidence from the EU wide stress test. Macroprudential Bulletin 9 (2019).Google Scholar
- Mike Mariathasan and Ouarda Merrouche. 2014. The manipulation of basel risk-weights. Journal of Financial Intermediation 23, 3 (2014), 300--321.Google ScholarCross Ref
- Patrick McConnell. 2013. Systemic operational risk: the LIBOR manipulation scandal. Journal of Operational Risk 8, 3 (2013), 59--99.Google Scholar
- Michael Sigmund and Christoph Siebenbrunner. 2021. The moral hazard problem in banks' risk reporting. Working paper (2021).Google Scholar
- Noah Simon and Robert Tibshirani. 2012. Standardization and the group lasso penalty. Statistica Sinica 22, 3 (2012), 983.Google ScholarCross Ref
- Robert Tibshirani. 1996. Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society: Series B (Methodological) 58, 1 (1996), 267--288.Google ScholarCross Ref
- F. Vallascas and J Hagendorff. 2013. The risk sensitivity of capital requirements: Evidence from an international sample of large banks. Review of Finance 17, 6 (2013), 1947--1988.Google ScholarCross Ref
- G. Verbeke and G. Molenberghs. 2000. Econometric Analysis (1. ed.). Springer.Google Scholar
- Ming Yuan and Yi Lin. 2006. Model selection and estimation in regression with grouped variables. Journal of the Royal Statistical Society: Series B (Statistical Methodology) 68, 1 (2006), 49--67.Google ScholarCross Ref
Index Terms
- Learning regulator influence on internal risk weights
Recommendations
Backtesting Marginal Expected Shortfall and Related Systemic Risk Measures
This paper proposes an original approach for backtesting systemic risk measures. This backtesting approach makes it possible to assess the systemic risk measure forecasts used to identify the financial institutions that contribute the most to the overall ...
OR Forum-Design of Risk Weights
Banking regulations set minimum levels of capital for banks. These requirements are generally formulated through a ratio of capital to risk-weighted assets. A risk-weighting scheme assigns a weight to each asset or category of assets and effectively ...
Geographic Diversification and Banks’ Funding Costs
We assess the impact of geographic diversification on a bank’s costs of interest-bearing liabilities. We employ a new identification strategy and discover that geographic expansion across U.S. states lowered funding costs. Consistent with expansion ...
Comments