Modelling systemic risk using neural network quantile regression

Bibliographic Data

ID21541806
AuthorsGeorg Keilbar (0000-0002-5574-3405, Humboldt-Universität zu Berlin, corresponding author), Ning Wang (0009-0007-8931-918X, University of York), Weining Wang (0000-0001-7299-6431)
Year2022
Volume62
Issue1
Pages93-118
Publication date2022-01-01
Open AccessYes
TypeARTICLE
VenueEmpirical Economics (JOURNAL)
Journal identifiersISSN: 0377-7332 • E-ISSN: 1435-8921
PublisherSpringer Science and Business Media LLC (PUBLISHER)
DOI10.1007/s00181-021-02035-1
OpenAlexW3133919534
LanguageEN
Citations received2
References cited30

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 the 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

Econometrics · Economics · Expected shortfall · Financial crisis · Quantile · Quantile regression · Risk management · Systemic risk · Value at risk · Complex Systems and Time Series Analysis · Computer Science · Financial Risk and Volatility Modeling · Market Dynamics and Volatility · Finance

Tools

Open DOIOpen Access