An alternative approach to predicting bank credit risk in Europe with Google data

Abstract

The aim of this paper is to construct an alternative approach based on a sentiment index to measure bank credit risk in European countries using an alternative approach instead of traditional measures. Specifically, we use Google data for a set of keywords related to bank credit risk to capture investor sentiment. The resulting index shows a great similarity to traditional indexes based on bank CDS. The out-of-sample analysis demonstrates that our sentiment index is helpful for predicting bank credit risk during periods of financial distress, since it enhances the accuracy of the estimations.