Title: Forecasting the insolvency of US banks using support vector machines (SVMs) based on local learning feature selection

Authors: Theophilos Papadimitriou; Periklis Gogas; Vasilios Plakandaras; John C. Mourmouris

Addresses: Department of Economics, Democritus University of Thrace, Thrace, Greece ' Department of Economics, Democritus University of Thrace, Thrace, Greece ' Department of Economics, Democritus University of Thrace, Thrace, Greece ' Department of Economics, Democritus University of Thrace, Thrace, Greece

Abstract: We propose a support vector machine (SVM)-based structural model to forecast the collapse of banking institutions in the USA using publicly disclosed information from their financial statements on a four-year rolling window. In our approach, the optimum input variable set is defined from a large data set using an iterative relevance-based selection procedure. We train an SVM model to classify banks as solvent and insolvent. The resulting model exhibits significant ability in bank default forecasting.

Keywords: bank insolvency; SVM; support vector machines; local learning; feature selection; insolvency forecasting; US banks; USA; United States; banking industry; financial statements; bank default; banking collapse.

DOI: 10.1504/IJCEE.2013.056267

International Journal of Computational Economics and Econometrics, 2013 Vol.3 No.1/2, pp.83 - 90

Published online: 05 Sep 2013 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article