Detail publikace

Bank-Sourced Transition Matrices: Are Banks’ InternalCredit Risk Estimates Markovian?

Autor: Ing. Mgr. Barbora Štěpánková M.A., Ph.D.,
Typ: Články v impaktovaných časopisech
Rok: 2021
Číslo: 0
ISSN / ISBN: DOI: 10.21314/JCR.2021.015
Publikováno v: Journal of Credit Risk
Místo vydání:
Klíčová slova: Risk management, Credit risk, Transition matrices, Banking
JEL kódy:
Granty: GAČR 18-05244S - Inovativní přístupy k řízení úvěrových rizik GAUK No. 1278218 Credit Transition matrices based on bank-sourced data and the business cycle PRIMUS/19/HUM/17 2019-2021 Behaviorální finance a makroekonomie: Nové pohledy pro hlavní proud
Abstrakt: This study explores banks' internal credit risk estimates and the associated bank-sourced transition matrices. We empirically test the widely used Markovian property and time homogeneity assumptions at an unprecedented scale. Our unique dataset consists of internal probability of default estimates from twelve global banks that employ advanced internal rating-based approach, covering monthly observations on 20,000 corporates over the 2015-2018 period. The results indicate that internal credit risk estimates do not satisfy the two assumptions, showing evidence of both path-dependency and time heterogeneity even within the period of economic expansion. Contradicting previous findings based on data from credit rating agencies, banks tend to revert their past rating actions. This has significant practical implications through bank-sourced credit transition matrices, which are becoming increasingly important as regulators begin to utilise more detailed credit risk datasets (e.g. AnaCredit by the ECB) with potential applications in stress-testing.
Leden 2022




Patria Finance