Financial Soundness Prediction Using a Multi-classification Model: Evidence from Current Financial Crisis in OECD Banks

D. Fernández-Arias (), M. López-Martín (), T. Montero-Romero (), F. Martínez-Estudillo () and F. Fernández-Navarro ()
Additional contact information
D. Fernández-Arias: Universidad Loyola Andalucia
M. López-Martín: Universidad Loyola Andalucia
T. Montero-Romero: Universidad Loyola Andalucia
F. Martínez-Estudillo: Universidad Loyola Andalucia
F. Fernández-Navarro: Universidad Loyola Andalucia

Computational Economics, 2018, vol. 52, issue 1, No 13, 275-297

Abstract: Abstract The paper aims to develop an early warning model that separates previously rated banks (337 Fitch-rated banks from OECD) into three classes, based on their financial health and using a one-year window. The early warning system is based on a classification model which estimates the Fitch ratings using Bankscope bank-specific data, regulatory and macroeconomic data as input variables. The authors propose a “hybridization technique” that combines the Extreme learning machine and the Synthetic Minority Over-sampling Technique. Due to the imbalanced nature of the problem, the authors apply an oversampling technique on the data aiming to improve the classification results on the minority groups. The methodology proposed outperforms other existing classification techniques used to predict bank solvency. It proved essential in improving average accuracy and especially the performance of the minority groups.

Keywords: Bankruptcy prediction; Artificial neural networks; Extreme learning machine; Early warning models; Computational intelligence; Financial crisis (search for similar items in EconPapers)
Date: 2018
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://link.springer.com/10.1007/s10614-017-9676-6 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

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:kap:compec:v:52:y:2018:i:1:d:10.1007_s10614-017-9676-6

Ordering information: This journal article can be ordered from
http://www.springer. ... ry/journal/10614/PS2

DOI: 10.1007/s10614-017-9676-6

Access Statistics for this article

Computational Economics is currently edited by Hans Amman

More articles in Computational Economics from Springer, Society for Computational Economics Contact information at EDIRC.
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().