A cluster analysis on the default determinants in the European banking sector

Abstract

The aim of this paper is to identify the relationship between banks’ probability of default and their risk taking incentives. Exploring a large set of bank level financial data from 203 European banks during 2005–2013 we apply the cluster analysis. The results indicate a number of two very different groups inside the dataset within each year, either using the hierarchical trees or the k-means clustering algorithms. Also, the composition of the clusters remains unchanged during crisis years compared with the pre-crisis for the vast majority of the instances. Finally, when mapping the clusters to the distance to default computed through the z-score variable, we show that banks with large size and high liquidity risk enhance their default risk.