Modelling Recovery Rate for Incomplete Defaults Using Time Varying Predictors

Abstract

The Internal Rating Based (IRB) approach requires that financial
institutions estimate the Loss Given Default (LGD) parameter not only based on
closed defaults but also considering partial recoveries from incomplete workouts.
This is one of the key issues in preparing bias-free samples, as there is a
need to estimate the remaining part of the recovery for incomplete defaults
before including them in the modeling process. In this paper, a new approach
is proposed, where parametric and non-parametric methods are presented to
estimate the remaining part of the recovery for incomplete defaults, in predefined intervals concerning sample selection bias. Additionally it is shown that
recoveries are driven by different set of characteristics when default is aging.
As an example, a study of major Polish bank is presented, where regression
tree outperforms other methods in the secured products segment, and fractional
regression provides the best results for non-secured ones.