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 systemic financial crises with recurrent neural networks, Journal of Financial Stability August (2020). Tölö, Eero

Category A Peer-reviewed scientific articles
Sub-category A1 Journal article (refereed), original research
auki Internal authors
Tölö Eero / Macroprudential Analysis Division
All authors as text Tölö, Eero 
Number of authors
Status Published
Year of publication 2020 
Date 31.05.2020 
Name of article Predicting systemic financial crises with recurrent neural networks 
Name of journal Journal of Financial Stability
Volume of issue 49 
Number of issue August 
Abstract We consider predicting systemic financial crises one to five years ahead using recurrent neural networks. We evaluate the prediction performance with the Jórda-Schularick-Taylor dataset, which includes the crisis dates and annual macroeconomic series of 17 countries over the period 1870−2016. Previous literature has found that simple neural net architectures are useful and outperform the traditional logistic regression model in predicting systemic financial crises. We show that such predictions can be significantly improved by making use of the Long-Short Term Memory (RNN-LSTM) and the Gated Recurrent Unit (RNN-GRU) neural nets. Behind the success is the recurrent networks’ ability to make more robust predictions from the time series data. The results remain robust after extensive sensitivity analysis.
Free text descriptor in Finnish pankkikriisit; pankit; riskit; kriisit; ennusteet; ennakointi; neuroverkot; 
Free text descriptor in English Early warning system; Systemic Banking crises; Neural networks; Validation 
JEL-codes G21, C45, C52 
ISSN / e-ISSN 1572-3089 
auki Internet addresses
Additional information Available online 31 May 2020.
Notes BoF 14/2019 

Related publications