SoleCRISTransition linkFrontpageTransition linkInstructionsTransition linkLogin Bank of Finland

A Peer-reviewed scientific articles/A1 Journal article (refereed), original research
This is the view page of publication. On this page you can view basic information of publication or go back on previous page using back-action on the bottom of the page. If you want to move to edit the information of publication, use the actions on the bottom of the page or continue using the system from menu.

Predicting Banking Crises with Artificial Neural Networks: The Role of Nonlinearity and Heterogeneity, Scandinavian Journal of Economics 1; January (2017). Ristolainen, Kim

Category A Peer-reviewed scientific articles
Sub-category A1 Journal article (refereed), original research
auki Internal authors
Ristolainen Kim / Research
All authors as text Ristolainen, Kim 
Number of authors
Status Published
Year of publication 2018 
Date 28.12.2017 
Name of article Predicting Banking Crises with Artificial Neural Networks: The Role of Nonlinearity and Heterogeneity 
Name of journal Scandinavian Journal of Economics
Volume of issue 120 
Number of issue 1; January 
Pages 31-62 
Abstract Studies of the early warning systems (EWSs) for banking crises usually rely on linear classifiers, estimated with international datasets. I construct an EWS based on an artificial neural network (ANN) model, and I also account for regional heterogeneity in order to improve the generalization ability of EWS models. All of the banking crises in my test set are then predictable at a 24-month horizon, using information from earlier crises. For some countries, estimation with a regional dataset significantly improves the predictions. The ANN outperforms the usual logit regression, assessed by the area under the receiver operating characteristics curve.
Free text descriptor in Finnish pankkikriisit; ennusteet; mallit; 
Free text descriptor in English artificial neural networks, banking crises, early warning system, financial stability 
ISSN / e-ISSN 0347-0520 
auki Internet addresses
Additional information First published: 28 December 2017