AUTHOR=Ren Chao , Zhu Ziyan , Zhou Donghai 

TITLE=Multi-quantile systemic financial risk based on a monotone composite quantile regression neural network

JOURNAL=Frontiers in Physics

VOLUME=12

YEAR=2024

URL=https://www.frontiersin.org/journals/physics/articles/10.3389/fphy.2024.1484589

DOI=10.3389/fphy.2024.1484589

ISSN=2296-424X

ABSTRACT=<p>This study proposes a novel perspective to calibrate the conditional value at risk (<italic>CoVaR</italic>) of countries based on the monotone composite quantile regression neural network (<italic>MCQRNN</italic>). <italic>MCQRNN</italic> can fix the “quantile crossing” problem, which is more robust in <italic>CoVaR</italic> estimating. In addition, we extend the <italic>MCQRNN</italic> method with quantile-on-quantile (<italic>QQ</italic>), which can avoid the bias in quantile regression. Building on the estimation results, we construct a systemic risk spillover network across countries in the Asia–Pacific region by considering the suffering and overflow effects. A comparison among <italic>MCQRNN</italic>, <italic>QRNN</italic>, and <italic>MCQRNN-QQ</italic> indicates the significance of monotone composite quantiles in modeling <italic>CoVaR</italic>. Additionally, the network analysis of composite risk spillovers illustrates the advantages of <italic>MCQRNN-QQ-CoVaR</italic> compared with <italic>QRNN-CoVaR</italic>. Moreover, the average composite systemic suffering index and the average composite systemic overflow index are introduced as country-specific measures that enable identifying systemically relevant countries during extreme events.</p>