Affiliations: University of Santiago de Compostela, Avda. do Burgo das Nacións, s/n. (Campus Norte), Santiago de Compostela, Spain
Correspondence:
[*]
Corresponding author. L. Otero-González, University of Santiago de Compostela, Avda.
do Burgo das Nacións, s/n. (Campus Norte), 15782 Santiago de Compostela, Spain. Tel.: +34647344011; E-mail: luis.otero@usc.es.
Note: [1] University of Illes Balears.
Abstract: The study analyses the effectiveness of the Early Warning System (EWS) for forecasting bank defaults during the recent financial crisis based on Moody’s KMV Expected Default Frequency (EDF) measure and accounting ratios using a sample of European listed banks. The Bank Financial Strength ratings D+ and below are used as a bank default indicator. Independent variables include 1-year and 5-year EDFs, one for the adverse selection effect and another for accounting ratios. Our results show that EDF metrics combined with four CAMEL covariates and the variable capturing adverse selection are able to predict the defaults of European banks up to 8 quarters before an event. When comparing the model with another only including the EDF indicator, the statistical significance improves considerably, suggesting that added variables provide additional information and power to the model. This study proposes possible improvements to the EWS which could be useful to identify inputs to incorporate in intelligent models.
Keywords: Early warning systems, CAMEL models, distance to default, expected default frequency, banks
