Application of Data Envelopment Analysis to Calculating Probability of Default for High Rated Portfolio

The aim of our research is to propose a method of rating companies which is based on efficiency measure given by Data Envelopment Analysis (DEA). Proper rating of borrowers is an essential requirement of PD estimation. The difficulty in DEA application is the selection of input and output from the set of indicators describing evaluated objects, which is usually based on expert knowledge. Therefore we apply random forests and gradient boosting to select financial indicators used by the DEA approach and to obtain a ranking of companies needed for PD estimation.