Explainable Graph Neural Networks for Interbank Contagion Surveillance: A Regulatory-Aligned Framework for the U.S. Banking Sector
Provides a transparent, regulatory-aligned GNN tool for macro-prudential surveillance of the U.S. interbank system, using only publicly available data.
The ST-GAT framework models 8,103 U.S. banks over 58 quarters to detect early signs of distress, achieving AUPRC of 0.939, nearly matching XGBoost (0.944), with ROA and NPL ratio as key predictors consistent with the 2023 regional banking crisis.
The Spatial-Temporal Graph Attention Network (ST-GAT) framework was created to serve as an explainable GNN-based solution for detecting bank distress early warning signs and for conducting macro-prudential surveillance of the interbank system in the United States. The ST-GAT framework models 8,103 FDIC insured institutions across 58 quarterly snapshots (2010Q1-2024Q2). Bilateral exposures were reconstructed from publicly available FDIC Call Reports using maximum entropy estimation to produce a dynamic directed weighted graph. The framework achieves the highest AUPRC among all GNN architectures (0.939 +/- 0.010), trailing only XGBoost (0.944). Ablation analysis confirms the BiLSTM temporal component contributes +0.020 AUPRC; temporal attention weights exhibit a monotonically decreasing pattern consistent with long-run structural vulnerability weighting. Permutation importance identifies ROA (0.309) and NPL Ratio (0.252) as dominant predictors, consistent with post-mortem analyses of the 2023 regional banking crisis. All data are publicly available FDIC Call Reports and FRED series; all code and results are released.