Deriving the term-structure of loan write-off risk under IFRS 9 by using survival analysis: A benchmark study

TL;DR

This paper compares survival analysis models for estimating loan write-off risk under IFRS 9, introducing a novel dichotomisation step and conducting a benchmark study to improve LGD modeling practices.

Contribution

It introduces a novel dichotomisation step in LGD modeling and compares survival models with logistic regression for write-off risk estimation under IFRS 9.

Findings

DtH-model outperforms other models in most diagnostics

Single-stage LGD-model yields best results due to L-shaped distribution

Survival models enhance understanding of write-off risk term-structure

Abstract

The estimation of marginal loan write-off probabilities is a non-trivial task when modelling the loss given default (LGD) risk parameter in credit risk. We explore two types of survival models in estimating the overall write-off probability over default spell time, where these probabilities form the term-structure of write-off risk in aggregate. These survival models include a discrete-time hazard (DtH) model and a conditional inference survival tree. Both models are compared to a cross-sectional logistic regression model for write-off risk. All of these (first-stage) models are then ensconced in a broader two-stage LGD-modelling approach, wherein a loss severity model is estimated in the second stage. In expanding the model suite, a novel dichotomisation step is introduced for collapsing the write-off probability into a 0/1-value, prior to LGD-calculation. A benchmark study is subsequently conducted amongst the resulting LGD-models. We find that the DtH-model outperforms other two-stage LGD-models admirably across most diagnostics. However, a single-stage LGD-model still had the best results, likely due to the peculiar `L-shaped' LGD-distribution in our data. Ultimately, we believe that our tutorial-style work can enhance LGD-modelling practices when estimating the expected credit loss under IFRS 9.