Abstract

Physical infrastructure failure induces topological phase transitions in financial networks that existing systemic risk models cannot detect, attribute, or govern. This study introduces CASCADEnt (Cascading Systemic-Entropy-Detecting Network), a physics-informed entropy protocol for infrastructure-coupled financial hypergraphs. The model integrates three components: (i) a Landauer-motivated entropy threshold (S*=2.852 nats) that detects imminent metabolic arrest before it manifests as market stress; (ii) Gradient-Boosted Integrated Gradients (GB-IG) metabolic centrality that attributes systemic collapse to the specific apex nodes driving it; and (iii) a Lyapunov-constrained Hamilton–Jacobi–Bellman protocol that governs macroprudential intervention with deterministic stability tendency under a linear control assumption (Theorem 1); stochastic extensions remain future work. The key variables are daily equity returns and hypergraph topology for 19 JSE Top40 securities, integrated with Eskom Energy Availability Factor (EAF) telemetry and CBOE VIX (T=2838 trading days, January 2015–April 2026). CASCADEnt achieves F1 = 0.643 at a 96 h early-warning lead time, outperforming all advance-warning baselines by 23.6 percentage points, with a false alarm rate of zero across 553 out-of-distribution days. Twelve apex nodes concentrate 85.5% of total system entropy, providing a governance target for macroprudential capital buffer design in infrastructure-dependent emerging economies.

IPC Classification

Keywords