Skip to content
View drewverzino's full-sized avatar

Block or report drewverzino

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
drewverzino/README.md

Hi, I'm Drew 👋

🎓 CS @ Georgia Tech · M.S. Quantitative & Computational Finance (incoming)
📊 Aspiring Quant Researcher / Trader / Developer
💻 Experience: Morgan Stanley (2x SWE Intern) · Equifax (ML Engineer Intern) · Georgia Tech Student Foundation (Senior Quant Director)


🚀 What I Do

  • ⚡ Build execution algorithms, trading signals, and backtesting frameworks
  • 📈 Research time-series models, volatility surfaces, and deep learning in markets
  • 🏦 Manage and mentor a 37-analyst team running a $50K quant portfolio inside a $2.6M endowment

🛠 Tech + Quant Stack

  • Languages: Python · C++ · SQL · Java · TypeScript
  • Libraries/Tools: NumPy · Pandas · scikit-learn · statsmodels · PyTorch · TensorFlow · Backtrader · Plotly/Dash
  • Quant: Factor modeling · Time-series (ARIMA/GARCH, SARIMA) · Monte Carlo simulation · Portfolio optimization · IBKR API
  • Infra: Kafka · Docker · Git · Linux · Azure DevOps

🔬 Selected Projects

  • 📊 Option-Density-Viz: Extracted risk-neutral densities from BTC/ETH options (Deribit API), fit arbitrage-free SVI smiles, applied Breeden–Litzenberger + COS methods, and built Plotly analytics dashboards
  • 🤖 Financial Markets RL Simulator: Built multi-agent RL limit order book simulator (SPY, BTC, 10Y); PPO/SAC agents achieved 39% CAGR and Sharpe 1.3 over 10 years
  • 📐 Neural PDE Models for Option Greeks: Built a physics-informed neural network embedding the Black–Scholes PDE to generate option Greeks across strikes and volatilities, delivering faster and more stable sensitivities than finite-difference and Monte Carlo methods
  • 🏦 Company Bankruptcy Predictor: Developed ML pipeline to forecast corporate bankruptcy using financial ratios. Trained Logistic Regression, Random Forest, SVM, Gradient Boosting, and Neural Nets; best model (SVM with RBF kernel) achieved ~96–97% accuracy with strong recall on bankruptcy cases.

🤝 Connect

Pinned Loading

  1. option-density-viz option-density-viz Public

    Risk-neutral probability density visualization from equity and crypto options (BTC/ETH).

    Python

  2. Green-Thumb Green-Thumb Public

    Forked from simisharma14/Hackathon_2025

    Python

  3. market-rl-simulator market-rl-simulator Public

    Python

  4. Neural-PDE-Option-Greeks Neural-PDE-Option-Greeks Public

    CS 4644/7643 Project — Physics-Informed Neural Networks for Option Greeks

    Jupyter Notebook

  5. GTSF-Quantitative-Sector/sarima_forecast GTSF-Quantitative-Sector/sarima_forecast Public

    Jupyter Notebook 2 2