Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/191248 
Year of Publication: 
2019
Series/Report no.: 
IWH Discussion Papers No. 2/2019
Publisher: 
Leibniz-Institut für Wirtschaftsforschung Halle (IWH), Halle (Saale)
Abstract: 
This paper compares the out-of-sample predictive performance of different early warning models for systemic banking crises using a sample of advanced economies covering the past 45 years. We compare a benchmark logit approach to several machine learning approaches recently proposed in the literature. We find that while machine learning methods often attain a very high in-sample fit, they are outperformed by the logit approach in recursive out-of-sample evaluations. This result is robust to the choice of performance measure, crisis definition, preference parameter, and sample length, as well as to using different sets of variables and data transformations. Thus, our paper suggests that further enhancements to machine learning early warning models are needed before they are able to offer a substantial value-added for predicting systemic banking crises. Conventional logit models appear to use the available information already fairly effciently, and would for instance have been able to predict the 2007/2008 financial crisis out-of-sample for many countries. In line with economic intuition, these models identify credit expansions, asset price booms and external imbalances as key predictors of systemic banking crises.
Subjects: 
early warning system
logit
machine learning
systemic banking crises
JEL: 
C35
C53
G01
Persistent Identifier of the first edition: 
Document Type: 
Working Paper

Files in This Item:
File
Size
910.17 kB





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