Predicting sovereign credit ratings for portfolio stress testing

Jonas De Oliveira Campino, Federico Galizia, Daniela Serrano and Frank Sperling
Additional contact information
Jonas De Oliveira Campino: Lead Strategic Risk Management Specialist in the Office of Risk Management, The Inter-American Development Bank, USA
Federico Galizia: Chief Risk Officer, The Inter-American Development Bank, USA
Daniela Serrano: Economist, The Inter-American Development Bank, USA
Frank Sperling: Unit Chief, The Inter-American Development Bank, USA

Journal of Risk Management in Financial Institutions, 2021, vol. 14, issue 3, 229-241

Abstract: This paper analyses the relationship between macroeconomic and credit cycles. It is not a straightforward relationship, particularly in sovereign credit assessment. Modelling such a relationship requires blending scenario analysis and stress testing, together with dynamic modelling of macroeconomic and credit variables. The novelty of the presented approach is its ability to cross-pollinate machine learning and Monte Carlo (MC) simulation as part of a process that overcomes the challenges faced by risk managers. The result is a probabilistic forward-looking view of credit risk scenarios that can guide action. Sovereign credit ratings are expert opinions based on relevant macroeconomic, financial and policy information. We introduce a predictive machine learning model of sovereign credit ratings that lends itself naturally to MC simulations and stress testing. The Least Absolute Shrinkage and Selection Operator (LASSO) allows considering many variables simultaneously in a nonlinear fashion as candidates for predicting sovereign ratings. The portfolio stress testing capability comes in by augmenting the set of variables used in the MC simulations to include external shock variables common to the sovereigns in the portfolio, for example, relevant global commodity prices. The resulting rating distribution can be used to calculate different relevant risk metrics, including credit-sensitive measures of risk-weighted assets.

Keywords: capital adequacy; sovereign risk; credit rating; stress testing; machine learning; LASSO; Monte Carlo simulation (search for similar items in EconPapers)
JEL-codes: E5 G2 (search for similar items in EconPapers)
Date: 2021
References: Add references at CitEc
Citations:

Downloads: (external link)
https://hstalks.com/article/6339/download/ (application/pdf)
https://hstalks.com/article/6339/ (text/html)
Requires a paid subscription for full access.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:aza:rmfi00:y:2021:v:14:i:3:p:229-241

Access Statistics for this article

More articles in Journal of Risk Management in Financial Institutions from Henry Stewart Publications
Bibliographic data for series maintained by Henry Stewart Talks ().