Machine learning as an early warning system to predict financial crisis

Author First name, Last name, Institution

Aristeidis Samitas, Zayed University
Elias Kampouris, Abu Dhabi University
Dimitris Kenourgios, National and Kapodistrian University of Athens

Document Type

Article

Source of Publication

International Review of Financial Analysis

Publication Date

10-1-2020

Abstract

© 2020 Elsevier Inc. This paper studies on “Early Warning Systems” (EWS) by investigating possible contagion risks, based on structured financial networks. Early warning indicators improve standard crisis prediction models performance. Using network analysis and machine learning algorithms we find evidence of contagion risk on the dates where we observe significant increase in correlations and centralities. The effectiveness of machine learning reached 98.8%, making the predictions extremely accurate. The model provides significant information to policymakers and investors about employing the financial network as a useful tool to improve portfolio selection by targeting assets based on centrality.

DOI Link

10.1016/j.irfa.2020.101507

ISSN

1057-5219

Publisher

Elsevier Inc.

Volume

71

First Page

101507

Disciplines

Business

Keywords

Contagion, Financial crisis, Forecasting, Machine learning, Social network analysis

Scopus ID

85085559699

Recommended Citation

Samitas, Aristeidis; Kampouris, Elias; and Kenourgios, Dimitris, "Machine learning as an early warning system to predict financial crisis" (2020). All Works. 2293.
https://zuscholars.zu.ac.ae/works/2293

Indexed in Scopus

yes

Open Access

no