I sit at the intersection of quantitative finance and machine learning β designing data-driven systems that extract signal from noise, price risk, and build edge in financial markets.
A full quant research pipeline β from raw data to risk-adjusted returns β with Monte Carlo optimization, efficient frontier construction, and rigorous out-of-sample validation.
| Metric | Result |
|---|---|
| π Rolling CAGR | 25%+ |
| β‘ Sharpe Ratio | ~1.0 |
| π‘οΈ Sortino Ratio | > 1.0 |
| π Benchmark | Outperforms SPY |
What's inside:
- π² Monte Carlo simulation β 2,000 portfolios per rebalance cycle
- π Efficient Frontier visualization with optimal Sharpe portfolio
- π Rolling backtest β 5-year train Β· 1-year test Β· annual rebalance
- π Full risk suite β VaR, CVaR, Sharpe, Sortino, drawdown analysis
- π Covariance & correlation matrix analysis
β¦ Stack: Python Β· Pandas Β· NumPy Β· SciPy Β· Plotly Β· Statsmodels
β¦ Optimization: Maximize Sharpe Ratio via Monte Carlo Β· Walk-forward validated
