Robust clustering of EU banking data

In this paper we present an application of robust clustering to the European Union (EU) banking system. Banking institutions may differ in several aspect, such as size, business activities and geographical location. After the latest financial crisis, it has become of paramount importance for the European regulators to identify common features and issues in the EU banking system and address them in all Member States (or at least those of the Euro area) in a harmonized manner. A key issue is to identify activities, in particular trading, which may impact on the stability of the whole EU banking sector. In this paper we show the use of robust clustering for this purpose. The data discussed cover the total volumes and relative share of the trading activities. Data, extracted from the SNL database, includes 245 banks from all EU27 countries, but Estonia, plus a Norwegian bank. At first glance, data appear not showing clear patterns and with standard clustering techniques, such as k-means, it is difficult to identify a separation even in this two-dimensional space. Robust clustering, in particular TCLUST, has allowed to get a better insight of the dataset.

PAGANO Andrea;  TORTI Francesca;  CARIBONI Jessica;  PERROTTA Domenico; 

2014-11-14

Cooperativa Libraria Editrice Università di Padova - CLEUP

JRC84375

978-88-67-87117-9,   

http://www.cladag2013.it/images/file/CLADAG2013_Abstract.pdf,    https://publications.jrc.ec.europa.eu/repository/handle/JRC84375,