03 — Research

Robust Quantitative Methods

I apply econometrics, robust statistics, and graph learning to systemic risk and financial decision problems.

• Econometrics
• Systemic Risk
• Economic Networks

To address instability and structural shocks in economic infrastructure, I integrate robust econometrics, extreme value theory, and graph neural networks. This approach enables early detection of financial contagion vectors, stress propagation in interbank market networks, and energy network vulnerability forecasting. The goal is to build quantitative decision-support frameworks that remain resilient under heavy-tailed distributions and structural market regime shifts.

Publications

• Network Topology Analysis and Machine Learning Techniques for Systemic Risk Prediction in U.S. Equity Markets Leveraging Graph Neural Networks (GNNs) and complex network theory to detect early warning signals of systemic risk in financial markets.
  • Systemic Risk
  • Graph Neural Networks
  • Network Science
  • Financial Machine Learning
• Robust Portfolio Optimization Under Systematic Market Disruptions: A Factor-Analytic Approach Based on my MSc thesis, this paper is currently in review at Computational Economics and develops a robust framework for portfolio optimization under contamination.
  • Quantitative Finance
  • Robust Statistics
  • Portfolio Optimization
  • High-Dimensional Data

Projects

• Gas Network Risk Forecasting Second-place hackathon project for gas leak risk prediction using geospatial-temporal features, synthetic data augmentation, and SHAP-based interpretability.
  • Hackathon
  • Side Quest
  • Forecasting
  • Imbalanced Learning
• Network Topology Analysis for Systemic Risk Prediction Financial machine learning project combining dynamic correlation networks, graph neural networks, and trading backtests to detect systemic risk in U.S. equity markets.
  • Research
  • Systemic Risk
  • Graph Neural Networks
  • Algo Trading
• Robust Portfolio Optimization under Systematic Market Disruptions (PFSE) Novel PFSE estimator achieves 25% breakdown point with 32× computational speedup over MCD. Out-of-sample Sharpe 1.87 on S&P 500 (2015–2025), 29% lower drawdown during COVID-19. Submitted to Computational Economics.
  • Research
  • Quantitative Finance
  • Robust Statistics
  • Portfolio Optimization

← All research