Skip to main content

ORIGINAL RESEARCH article

Front. Phys.
Sec. Social Physics
Volume 12 - 2024 | doi: 10.3389/fphy.2024.1484589

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

Provisionally accepted
Chao Ren Chao Ren 1*Ziyan Zhu Ziyan Zhu 2Donghai Zhou Donghai Zhou 2
  • 1 Anhui Business College, Wuhu, China
  • 2 Southeast University, Nanjing, Jiangsu Province, China

The final, formatted version of the article will be published soon.

    This study aims to propose a novel perspective to calibrate the conditional value-at-risk (CoVaR) of countries based on the monotone composite quantile regression neural network (MCQRNN). MCQRNN can fix the "quantile crossing" problem, which is more robustness in CoVaR estimating. Besides, we extend the MCQRNN method with quantile-on-quantile (QQ), which can avoid the bias in quantile regression. Building on the estimation results, we construct the systemic risk spillover network across countries in Asia-Pacific region by considering the suffering and overflowing effects. A comparison among MCQRNN, QRNN and MCQRNN-QQ indicates the significance of monotone composite quantile in modelling CoVaR. Additionally, the network analysis of composite risk spillovers is stated to illustrate the advantages of MCQRNN-QQ-CoVaR compared with QRNN-CoVaR. Moreover, the average composite systemically suffering index and the average composite systemically overflowing index are introduced as country-specific measures, which enable to identify systemically relevant countries during the extreme events.

    Keywords: multiple quantile risk spillover, MCQRNN, QQ-CoVaR, Systemic financial risk, Quantile crossing

    Received: 24 Aug 2024; Accepted: 09 Oct 2024.

    Copyright: © 2024 Ren, Zhu and Zhou. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Chao Ren, Anhui Business College, Wuhu, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.