Anticipating bank distress in the Eurozone: An Extreme Gradient Boosting approach

Francisco Climent, Alexandre Momparler and Pedro Carmona

Journal of Business Research, 2019, vol. 101, issue C, 885-896

Abstract: The banking sector plays a special role in the economy and has critical functions which are essential for economic stability. Hence, systemic banking crises disrupt financial markets and hinder global economic growth. In this study, Extreme Gradient Boosting, a state of the art machine learning method, is applied to identify a set of key leading indicators that may help predict and prevent bank failure in the Eurozone banking sector. The cross-sectional data used in this study consists of 25 annual financial ratio series for commercial banks in the Eurozone. The sample includes Eurozone listed failed and non-failed banks for the period 2006–2016. A number of early warning systems and leading indicator models have been developed to prevent bank failure. Yet the breadth and depth of the recent financial crisis indicates that these methods must improve if they are to serve as a useful tool for regulators and managers of financial institutions. Our goal is to build a classification model to determine which variables should be monitored to anticipate bank financial distress. A set of key variables are identified to anticipate bank defaults. Identifying leading indicators of bank failure is necessary so that regulators and financial institutions' management can take preventive and corrective measures before it is too late.

Keywords: Bank failure prediction; Bank failure prevention; Bank financial distress; Machine learning; Extreme Gradient Boosting; XGBoost (search for similar items in EconPapers)
Date: 2019
References: Add references at CitEc
Citations: View citations in EconPapers (28)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0148296318305678
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:jbrese:v:101:y:2019:i:c:p:885-896

DOI: 10.1016/j.jbusres.2018.11.015

Access Statistics for this article

Journal of Business Research is currently edited by A. G. Woodside

More articles in Journal of Business Research from Elsevier
Bibliographic data for series maintained by Catherine Liu ().