Hungary’s Corporate Sector Risk: A Machine Learning Approach

Author/Editor:

Jakree Koosakul ; Xuege Zhang

Publication Date:

August 13, 2024

Electronic Access:

Free Download. Use the free Adobe Acrobat Reader to view this PDF file

Summary:

In recent years, Hungary’s non-financial corporations were confronted with multiple shocks, ranging from the pandemic and rising geopolitical tensions to the historic tightening of domestic monetary policy. Employing machine learning techniques, this paper examines the determinants of Hungarian listed firms’ credit risk evolution over this period. Our analysis shows that both firm-specific and macroeconomic factors played a role in explaining the observed rise in firms’ default probability at onset of the pandemic, although Hungarian corporates proved broadly resilient, with risk indicators quickly improving a year after. Firms’ credit risk rose again in 2022, however, as both long-term interest rates and sovereign risk premia sharply increased, despite continued improvements in firms’ financial ratios. This development merits continued monitoring, particularly since a significant portion of corporate loans are set to mature within the next few years and could be repriced at higher interest rates.

Series:

Selected Issues Paper No. 2024/038

Subject:

Frequency:

Regular

English

Publication Date:

August 13, 2024

ISBN/ISSN:

9798400287916/2958-7875

Stock No:

SIPEA2024038

Format:

Paper

Pages:

12

Please address any questions about this title to publications@imf.org