🎯 Quant-focused MSc Finance (HEC Lausanne) with expertise in systematic strategies, portfolio optimization, and risk modeling.
🔬 I build deployable research pipelines that combine finance and machine learning — from clean point-in-time data, through labeling and modeling, to calibrated probability-aware execution.
🚀 My goal: contribute to hedge fund–style systematic research and portfolio management.

• 📈 Meta-Labeling Alpha Filter – AI-driven trade signal refinement for systematic equity strategies
• 🧮 Systematic Portfolio Optimization – robust optimization with tail-aware risk measures (CVaR, CDaR, Omega)
• 🤖 Expanding skills in ML/AI for time-series finance (LightGBM, MLPs, calibration, explainability)
• ⚙️ Strengthening C++ for performance-critical quant research environments

A deployable ML framework that learns when not to trade.

• End-to-end pipeline: point-in-time data → triple-barrier labeling → feature engineering → calibrated ML models (LightGBM, MLP).
• Probability-aware trade gating & sizing with volatility targeting, leverage caps, and turnover controls.
• Results (OOS, net of costs): Sharpe 1.09 in 50/50 blend with SPY; 65.8% win rate across 3,600+ trades.
• 📄 Full case report included | 🐍 Python code | 🔍 Reproducible runs with config snapshots

MSc thesis project on hedge fund allocation.

• Hybrid optimization framework integrating AR-EGARCH volatility, EVT for tails, Student-t copulas for dependencies.
• Objectives: CVaR, CDaR, Omega ratio; non-linear constraints (turnover, correlations).
• Tested on 30+ years of HFR data; outperformed traditional benchmarks in risk-adjusted returns.
• 📄 Thesis PDF included | 🐍 Python code | 📊 Full documentation & results

Programming & Tools
Python (Advanced), Git & GitHub, Linux (Dev use), SQL, Bloomberg Terminal, C++ (progressing)

Quant & Risk
Portfolio Optimization, Risk Management, Backtesting, Constrained Optimization, Tail Risk Modeling (AR/GARCH, EVT, Copulas)

Machine Learning
Supervised Learning (Classification & Regression), Ensemble Methods (LightGBM, MLP), Bayesian Optimization, Probability Calibration (vector-scaled softmax, blending), Model Validation & Explainability (SHAP)

Data Handling
Point-in-Time Data Construction, Feature Engineering, Time-Series Analysis, Data Wrangling & Visualization

📍 Based in Switzerland
🔗 LinkedIn – Gautier Petit
💻 GitHub – gautierpetit
🤝 Open to quant research / systematic strategy roles