I build computational tools at the intersection of quantitative finance and data engineering. My work focuses on portfolio optimization, probabilistic modeling, and the design of systems that turn raw market data into structured, actionable insight.

My current research centers on Cognitive Graph Portfolio Optimization (CGPO) : a framework that combines graph theory and cognitive computing to optimize asset allocation and minimize portfolio risk in non-stationary markets.

Outside of that, I work on stochastic process theory, derivative pricing models, and the infrastructure side of financial pipelines: data ingestion, factor construction, and backtesting architecture.

An adaptive portfolio allocation framework that integrates graph theory with cognitive computing. The project models asset relationships as dynamic networks to optimize risk-adjusted returns in non-stationary markets.

Technical Core

• Graph Engine — network-based asset dependency modeling.
• Market Environment — custom simulation logic for regime-switching scenarios.
• Optimization — algorithms for strategic portfolio rebalancing and risk mitigation.

Tracks four indices relevant to my research universe. Auto-updated every 6 hours on trading days via GitHub Actions.

_{Last updated: 2026-05-07 19:39 UTC}

Quantitative & Mathematical

• Portfolio optimization: mean-variance, Black-Litterman, factor models, shrinkage estimation
• Stochastic calculus, Black-Scholes framework, Monte Carlo simulation
• Statistical inference, time-series analysis, regime-switching models
• Risk metrics: VaR, CVaR, Sharpe ratio, Sortino ratio, maximum drawdown

Programming & Scripting

Data Science & Machine Learning

Infrastructure & DevOps

_{Open to quantitative research roles, fintech internships, and open-source collaboration on financial tools.}