Modelling Systemic Risk Using Neural Network Quantile Regression

27 Pages Posted: 29 Sep 2020

See all articles by Georg Keilbar

Georg Keilbar

Humboldt-Universität zu Berlin

Weining Wang

affiliation not provided to SSRN; University of York

Date Written: September 3, 2020


We propose a novel approach to calibrate the conditional value-at-risk (CoVaR) of financial institutions based on neural network quantile regression. Building on the estimation results, we model systemic risk spillover effects in a network context across banks by considering the marginal effects of the quantile regression procedure. An out-of-sample analysis shows great performance compared to a linear baseline specification, signifying the importance that nonlinearity plays for modelling systemic risk. We then propose three network-based measures from our fitted results. First, we use the Systemic Network Risk Index (SNRI) as a measure for total systemic risk. A comparison to existing network-based risk measures reveals that our approach offers a new perspective on systemic risk due to the focus on the lower tail and to the allowance for nonlinear effects. We also introduce the Systemic Fragility Index (SFI) and the Systemic Hazard Index (SHI) as firm-specific measures, which allow us to identify systemically relevant firms during the financial crisis.

Keywords: Systemic risk, CoVaR, Quantile regression, Neural networks

Suggested Citation

Keilbar, Georg and Wang, Weining and Wang, Weining, Modelling Systemic Risk Using Neural Network Quantile Regression (September 3, 2020). Available at SSRN: or

Georg Keilbar (Contact Author)

Humboldt-Universität zu Berlin ( email )

Humboldt Universität
Unter den Linden 6
Berlin, 10099

Weining Wang

University of York ( email )

Department of Economics and Related Studies Univer
York, YO10 5DD
United Kingdom

affiliation not provided to SSRN

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Abstract Views
PlumX Metrics