Qualitative judgement in public credit ratings: A proposed supporting approach using Self-Organising Maps (SOMs)

The financial crisis that began in late 2007 has raised awareness on the need to properly measure credit risk, placing a significant focus on the accuracy of public credit ratings. The objective of this paper is to present an automated credit rating model that dispenses with the excessive qualitative input that, during the years leading to the 2007 crisis, may have yielded results inconsistent with true counterparty risk levels. Our model is based on a mix of relevant credit ratios, historical data on a corporate universe comprising the global pharmaceutical, chemicals and Oil & Gas industries and a powerful clustering mathematical algorithm, Self-Organising Maps, a type of neural network. (C) 2014 Asociacion Cuadernos de Economia. Published by Elsevier Espana, S.L.U. All rights reserved.