Title Financial Soundness Prediction Using a Multi-classification Model: Evidence from Current Financial Crisis in OECD Banks
Authors GUERRERO ARIAS, ISMAEL, LÓPEZ MARTÍN, MARÍA DEL CARMEN, MONTERO ROMERO, Mª TERESA, MARTÍNEZ ESTUDILLO, FRANCISCO JOSÉ, FERNÁNDEZ NAVARRO, FRANCISCO DE ASÍS, LÓPEZ MARTÍN, MARÍA DEL CARMEN, MARTÍNEZ ESTUDILLO, FRANCISCO JOSÉ, MONTERO ROMERO, Mª TERESA, FERNÁNDEZ NAVARRO, FRANCISCO DE ASÍS, GUERRERO ARIAS, ISMAEL
External publication No
Means Comput. Econ.
Scope Article
Nature Científica
JCR Quartile 3
SJR Quartile 2
JCR Impact 1.18500
Area International
Web https://www.scopus.com/inward/record.uri?eid=2-s2.0-85015617440&doi=10.1007%2fs10614-017-9676-6&partnerID=40&md5=a36e8a29ba89907fb434b84340e74948
Publication date 01/06/2018
ISI 000435355300013
Scopus Id 2-s2.0-85015617440
DOI 10.1007/s10614-017-9676-6
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
Universidad Loyola members