Classification of the risk in the new financing framework of the Deposit Guarantee Systems in Europe: K-Means Cluster Analysis and Soft Computing

Abstract

The guidelines published by the European Banking Authority in 2015 about the contributions to the Deposit Guarantee Systems, establish two approaches to classify the member entities’ risk: the bucket method and the sliding scale method, allowing freedom to every Member State to decide which methodology to use. In this work, using the bucket method with two different clustering techniques, k-means and soft computing, in a sample that represents more than 90% of the deposits covered in the Spanish banking system during the 2008 to 2014 period, the differences in the distribution of the Deposit Guarantee Fund risk and in the entities’ contributions is analyzed. The obtained results reveal important differences. Consequently, the technique chosen by each country will determine the contributions regime.

Keywords

• Deposit Guarantee Systems
• European banking system
• banking regulation
• risk classification
• K-means
• soft computing