Addressing the limitations of conventional financial time series models in capturing modern market dynamics, this study introduces a novel financial monitoring framework based on Temporal Attentive Graph Networks (TAGN). The TAGN model integrates Graph Attention Networks (GAT) and Gated Recurrent Units (GRU) to simultaneously capture spatial dependencies among financial entities and the dynamic evolution of network structure. The framework uses a multi-relational dynamic graph of 50 NASDAQ stocks. Node features fuse multi-scale information (micro, meso, macro), and the graph structure integrates price correlation, supply chain, and institutional co-holdings. Compared to benchmarks (Logistic Regression, GCN, GCN-LSTM), TAGN demonstrates superior performance (AUC: 0.89) in predicting stocks likely to experience extreme volatility (>±15%) within three months. Empirical analysis (2018–2023) effectively quantifies network imprints of major events (e.g., 45% average edge weight surge during COVID-19; community stability Jaccard similarity drop to 0.34 following the SVB incident). An ablation study confirms the critical contribution of the attention and temporal components. Finally, by generating a risk early-warning index integrating network topology and model output, this research offers a new tool for systemic risk quantification and proactive anticipation.
Systemic risk propagation in modern financial markets is characterized by non-linear contagion and rapid topological evolution, rendering traditional static monitoring methods ineffective. Existing Graph Neural Networks (GNNs) often struggle to capture “structural breaks” during crises due to their reliance on static adjacency assumptions and isotropic aggregation. To address these challenges, this study proposes the Temporal Attentive Graph Networks (TAGN), a dynamic framework designed for extreme volatility prediction and financial surveillance. TAGN constructs an incremental multi-scale graph by fusing high-frequency trading data, supply chain linkages, and institutional co-holdings to model heterogeneous risk transmission channels. Technically, it employs a deeply coupled GAT-GRU architecture, where the Graph Attention Network (GAT) dynamically assigns weights to contagion sources, and the Gated Recurrent Unit (GRU) memorizes the trajectory of structural evolution. Extensive experiments on the S&P 500 dataset (2018–2024) demonstrate that TAGN significantly outperforms state-of-the-art baselines, including WinGNN and PatchTST, achieving an AUC of 0.890 and a Precision at 50 of 61.5%. Notably, a risk early-warning index derived from TAGN exhibits a 1–2 week lead time over the VIX index during major market stress events, such as the Silicon Valley Bank collapse. This research facilitates a paradigm shift from historical statistical estimation to dynamic network-aware sensing, offering interpretable tools for RegTech applications.