Dynamic financial tail risk networks: A backtesting-based conditional expected shortfall approach
Donghao Zhang, Xiaodong Yan, Feng Shen · 2026
Read Dynamic financial tail risk networks: A backtesting-based conditional expected shortfall approach by Donghao Zhang, Xiaodong Yan, Feng Shen (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0351966.txt.
Description
Donghao Zhang, Xiaodong Yan, and Feng Shen built a better way to map how extreme losses could jump between Chinese financial firms. Standard tools for tail risk, the rare bad days that cause crises, often fail their own accuracy tests. Their method blends a factor model with flexible dependence patterns and checks itself by backtesting, comparing predicted joint crashes with what the math says should happen.
The new model failed its backtests far less often than the rival versions, with rejection rates cut by roughly half against two of them. Applied to listed Chinese financial institutions, the risk network it drew lined up with real market stress events. Regulators watching for contagion get a network map that has passed stricter honesty checks, and a clearer view of which firms sit at the web's risky center.
Catalog record
| CREATOR | Donghao Zhang, Xiaodong Yan, Feng Shen |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 69591 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |