Empirical Performance of LGD Prediction Models

Journal of Risk Model Validation, Vol. 5, No. 2, 2011, pp. 25-44

26 Pages Posted: 11 Apr 2011 Last revised: 13 Nov 2013

See all articles by Benjamin Bade

Benjamin Bade

Leibniz Universit├Ąt Hannover

Daniel Roesch

University of Regensburg

Harald (Harry) Scheule

University of Technology Sydney (UTS) - School of Finance and Economics; Financial Research Network

Date Written: May 19, 2011

Abstract

The Global Financial Crisis highlighted that default and recovery rates of multiple borrowers generally deteriorate jointly during economic downturns. The vast majority of the literature, as well as many industry credit portfolio risk models ignore this and analyze default probabilities and recoveries in the event of default separately. As a result, the models project losses which are too low in economic downturns such as the recent financial crisis. Nevertheless, alternatives of incorporating the dependence between probabilities of default and recovery rates have been proposed. This paper is the first of its kind to assess the performance of these structurally different approaches. Four banks using different estimation procedures are compared. We use RMSE and RAE to measure the predictive accuracy of each procedure. The results show, that indeed models accounting for the correlation of default and recovery perform better than models ignoring it.

Keywords: Asset Value, Correlation, Credit Portfolio, Loss Given Default, Probability of Default, Recovery, Forecasting

JEL Classification: G20, C51, C52

Suggested Citation

Bade, Benjamin and Roesch, Daniel and Scheule, Harald, Empirical Performance of LGD Prediction Models (May 19, 2011). Journal of Risk Model Validation, Vol. 5, No. 2, 2011, pp. 25-44, Available at SSRN: https://ssrn.com/abstract=1806011 or http://dx.doi.org/10.2139/ssrn.1806011

Benjamin Bade (Contact Author)

Leibniz Universit├Ąt Hannover ( email )

Institut fur Rechnungslegung und WP
Koenigsworther Platz 1
Hannover, 30167
Germany

Daniel Roesch

University of Regensburg ( email )

Chair of Statistics and Risk Management
Faculty of Business, Economics and BIS
Regensburg, 93040
Germany

HOME PAGE: http://www-risk.ur.de/

Harald Scheule

University of Technology Sydney (UTS) - School of Finance and Economics ( email )

P.O. Box 123
Broadway, NSW 2007
Australia

HOME PAGE: http://https://www.uts.edu.au/staff/harald.scheule

Financial Research Network ( email )

C/- University of Queensland Business School
St Lucia, 4071 Brisbane
Queensland
Australia

HOME PAGE: http://www.firn.org.au

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
432
Abstract Views
1,537
rank
74,185
PlumX Metrics