Financial Crisis Prediction: A Model Comparison

9 Pages Posted: 1 Dec 2017

See all articles by Daniel Fricke

Daniel Fricke

Deutsche Bundesbank; University College London; London School of Economics & Political Science (LSE) - Systemic Risk Centre

Date Written: November 29, 2017

Abstract

In this paper we compare different models for financial crisis prediction, focusing on methods from the field of Machine Learning (ML). These methods are particularly promising, since they were specifically designed for making predictions. In our application, we find that the performance on these methods depends on whether we look at in-sample or out-of-sample predictions. In the latter case, they do not always outperform more traditional approaches (such as Logistic regressions). Nevertheless, we find that these methods can be useful and should therefore become a standard element in the toolbox of empirical researchers.

Keywords: Financial Crisis, Prediction, Classification, Machine Learning

JEL Classification: C38, C53, G01

Suggested Citation

Fricke, Daniel, Financial Crisis Prediction: A Model Comparison (November 29, 2017). Available at SSRN: https://ssrn.com/abstract=3059052 or http://dx.doi.org/10.2139/ssrn.3059052

Daniel Fricke (Contact Author)

Deutsche Bundesbank ( email )

Wilhelm-Epstein-Str. 14
Frankfurt/Main, 60431
Germany

University College London ( email )

Gower Street
London, WC1E 6BT
United Kingdom

London School of Economics & Political Science (LSE) - Systemic Risk Centre

Houghton St, London WC2A 2AE, United Kingdom
London

Register to save articles to
your library

Register

Paper statistics

Downloads
229
Abstract Views
706
rank
133,363
PlumX Metrics