Page 417 - Special Topic Session (STS) - Volume 3

STS552 Natalia Nehrebecka

Forecasting the recovery rate of non-financial
corporations with particular emphasis on
sectorial analysis
Natalia Nehrebecka
Narodowy Bank Polski

Abstract
The empirical literature on credit risk is mainly based on modelling the
probability of default, omitting the modelling of the loss on default. This paper
is aimed to study the recovery rate in theoretical approach - familiarizing with
regulatory requirements, and also in practical approach - to predict recovery
rates on the rarely applied here nonparametric method of Quantile Regression
and Bayesian Model Averaging, developed on the basis of individual
prudential and balance of payments data in the 2007–2018. Literature on
Losses Given Default focuses on mean predictions, even though losses are
extremely skewed and bimodal. The models were created on financial and
behavioural data that present the history of the credit relationship of the
enterprise with financial institutions. Two approaches are presented in the
paper: Point in Time and Through-the-Cycle. Using the estimated risk
parameter, the reserves for expected loan losses were also calculated. A
correct estimation of LGD parameter affects the appropriate amounts of held
reserves, which is crucial for the proper functioning of the bank and not
exposing itself to the risk of insolvency if such losses occur.

Keywords
loss given default; recovery rate; regulatory requirements; quantile regression;
bayesian model averaging

1. Introduction
Credit risk assessment (in particular ensuring accurate and reliable credit
ratings) plays a key role for many market participants. According to the
traditional approach the definition of credit risk, it is the risk of loss caused by
a debtor’s failure to repay a loan, while in the market definition it is the risk of
loss driven by a rating downgrade (i.e. an increase in the probability of default)
or failure to repay an obligation by a debtor. Basel Committee explains a
default event on a debt obligation in the two following ways:
- It is unlikely that the obligor will be able to repay its debt to the bank without
giving up any pledged collateral;
- The obligor is more than 90 days past due on a material credit obligation.
Basel II introduced the Internal Ratings-based Approach which enables
institutions to provide their own estimates for the Loss Rate Given Default (LGD).

406 | I S I W S C 2 0 1 9