Financial Crisis Prediction: A Model Comparison

9 Pages Posted: 1 Dec 2017

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

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
558
Abstract Views
1,924
Rank
90,781
PlumX Metrics