Research on systemic risk measurement based on temporal financial knowledge graph: Evidence from China

Z. Liu, Y. Zhang () and H. Chen
Additional contact information
Y. Zhang: Audencia Business School

Post-Print from HAL

Abstract: The inherent complexity and interconnectedness of systemic financial risks necessitate sophis ticated measurement frameworks, especially as new financial forms emerge and the economic environment becomes more complex. This paper aims to develop a novel composite systemic risk model using the financial knowledge graph for risk measurement. Notably, our research in corporates traditional financial institutions and FinTech entities, extending beyond conventional financial risk analytical boundaries. Empirical results show the model boosts risk measurement accuracy and is responsive to classic contingencies and inclusive finance policies. FinTech and securities sectors prove more susceptible to systemic risk than banking and insurance, with FinTech being easily influenced by high-tech enterprise support and FinTech-related regulatory policies, and securities by monetary policy. Moreover, institutions' performance is consistent across risk event types, while top risk contributors are evenly distributed across diverse financial sectors and account for the lion's share of the industry's systemic risk and exhibit risk aggregation.

Keywords: Knowledge graphs; Systemic risk; Risk measurement (search for similar items in EconPapers)
Date: 2025-12
Note: View the original document on HAL open archive server: https://hal.science/hal-05306849v1
References: Add references at CitEc
Citations:

Published in Pacific-Basin Finance Journal, 2025, 94 (2025), pp.102924. ⟨10.1016/j.pacfin.2025.102924⟩

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:hal-05306849

DOI: 10.1016/j.pacfin.2025.102924

Access Statistics for this paper

More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().