Python implementation of advanced financial network analysis toolkit for creating multi-layered Digital Twins of market dynamics. Implements information-theoretic Transfer Entropy and stochastic Kramers-Moyal methods to map non-linear, directed relationships between assets during normal and crisis periods.

Network-based early warning system for equity market crashes using S&P 500 sector correlation biomarkers, XGBoost, and sector rotation signals | Under journal review

Reproducible pipeline for modeling financial markets with correlation-based networks and Graph Neural Networks (GNN). Builds financial asset graphs from historical data, computes network metrics, and trains GNNs to learn relational representations for market analysis.

End-to-End Python implementation of the Mesoscopic Structural Risk-Navigation System from Shao, Yang & Zhang (2026). Estimates rolling QVAR models, extracts multiscale network backbones via Disparity Filter, enumerates 13 directed triadic motifs (30 node orbits), and optimizes a Minimum Structural Similarity Portfolio.

Multi-layer network analysis of cross-asset topology and cluster migration under geopolitical stress. 96 ETFs, 16 years (2010-2026), Leiden clustering, HMM regime detection, transfer entropy. Educational research.

Asymmetric liquidity flow dynamics in financial networks, interpreted via effective geometry and stability under the Victoria-Nash Asymmetric Equilibrium (VNAE).