January 2020
·
38 Reads
·
3 Citations
Lecture Notes in Computer Science
This paper describes a machine learning technique to timely identify cases of individual bank financial distress. Our work represents the first attempt in the literature to develop an early warning system for small European banks. We employ a machine learning technique, and build a decision tree model using a dataset of official supervisory reporting, complemented with qualitative banking sector and macroeconomic features. We propose a new and wider definition of financial distress, in order to capture bank distress cases at an earlier stage with respect to the existing literature on bank failures; in this way we identify bank crises at an early stage, therefore leaving a time window for supervisory intervention. We use the Quinlan’s C5.0 algorithm to estimate the model, whose final form comprises 12 features and 19 nodes, and outperforms a logit model estimation which we use to benchmark our analysis.