The use of non-parametric statistical methods, the development of models geared towards the homogeneous characteristics of corporate sub-populations, and the introduction of non-financial variables, are three main issues analysed in this paper. This study compares the predictive performance of a non-parametric methodology, namelyClassification/Regression Trees (CART), against traditional logistic regression (LR) by employing a vast set of matched-pair accounts of the smallest enterprises, known as micro-entities,from the United Kingdom for the period 1999 to 2008 that includes financial, non-financial, and macroeconomic variables. Our findings show that CART outperforms the standard approach in the literature, LR.

The severity loss distribution is the main topic in operational risk estimation. Numerous modelling methods have been suggested although very few work for both high frequency small losses and low frequency big losses. In this paper several methods of estimation are explored. The good performance of the double transformation kernel estimation in the context of operational risk severity is worthy of a special mention. This method is based on the work of Bolance and Guillen (2009), it was initially proposed in the context of cost of claims insurance, and it supposes an advance in operational risk research.