Skip to content

Author

Jin-Rui Zhang

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Conference Open access Jul 2026

Trade Policy Uncertainty and Systemic Risk in Commercial Banks: Empirical Evidence from the China–U.S. Trade War

China–U.S. trade tensions and rising trade policy uncertainty (TPU) have become an important external source of financial instability. This paper examines how TPU affects systemic risk in the real sector using China’s A-share non-financial listed firms as the sample, with a focus on the transmission channels underlying this process. Methodologically, the study constructs a CoVaR framework to measure firms’ contributions to systemic risk and applies event study methods together with fixed-effects models for empirical identification. The results indicate that higher TPU is associated with a persistent increase in firms’ systemic risk contribution, and the effect does not dissipate quickly over time. The transmission of this risk is primarily driven by disruptions in supply chains and tighter financing conditions, particularly through trade credit contraction, while expectation-driven channels, consistent with real options effects, also play an important role. Heterogeneity analysis further shows that firms with greater overseas exposure and higher supply chain dependence respond more strongly to TPU shocks, and the effects are more pronounced for firms located in eastern coastal regions. Overall, the findings provide micro-level evidence on how real-sector risk is transmitted to the broader financial system under geopolitical uncertainty, with implications for strengthening supply chain resilience and improving systemic risk management.

Jin-Rui Zhang, Chenhao He, Yuxuan Liu et al. · 0 citations
#artificial intelligence Preprint Sep 2026

GraphFAS: A Distributed System for Automated Graph Feature Generation and Selection in Industrial Transaction Networks

Industrial fraud detection often relies on costly expert-crafted features that overlook graph-structured relational signals, while GNNs often do not meet the interpretability and deployment requirements of financial risk control. We propose GraphFAS (Graph Feature Automated Selection), a distributed feature selection procedure based on Boruta that bridges this gap through: (1) a non-parametric graph feature generation module that constructs explicit, interpretable structural features via multi-hop subgraph extraction and multi-scale aggregation without learned parameters; and (2) an automated distributed feature selection algorithm extending Boruta with median-based aggregation across partitions to robustly identify informative features at scale with minimal domain expertise. Compared with end-to-end GNN pipelines, GraphFAS decouples feature aggregation from model training, enabling direct integration with tabular models and direct compatibility with TreeSHAPbased explanations. Deployed in Alipay, GraphFAS delivers orderof-magnitude improvements in engineering efficiency while showing strong performance against expert-driven and graph-learning baselines on large-scale graphs.

Yi-Ce Luo, Yun Zhu, Xi Chen et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.