Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/340337 
Year of Publication: 
2022
Citation: 
[Journal:] Borsa İstanbul Review [ISSN:] 2214-8469 [Volume:] 22 [Issue:] 6 [Year:] 2022 [Pages:] 1132-1144
Publisher: 
Elsevier, Amsterdam
Abstract: 
Financial sector distress is a situation in which financial intermediation is either costly or impossible (or both) as proxied by tight financial conditions - high spreads, decline in equity value and high volatility. Tight financial conditions have been identified as a risk factor to the medium-run GDP growth. I therefore use different statistical methods aiming at extracting early warning signals from the cross-country data related to financial health and soundness of countries’ financial systems. The novelty of my approach is that I account for class imbalance - that is I adjust my results for the fact that financial distress periods are rare events. I contrast that to the previous literature. I find that it is possible to generate accurate warning signals about future distress well in advance and suggest which variables should be closely monitored as sources of financial vulnerabilities.
Subjects: 
Financial system distress
Machine learning
Early warning signals
Financial conditions
JEL: 
C404aE44
E60
G01
Persistent Identifier of the first edition: 
Creative Commons License: 
cc-by-nc-nd Logo
Document Type: 
Article
Appears in Collections:

Files in This Item:
File
Size





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.