Quant with a background in mathematics, philosophy, and financial modelling. I build interpretable models under uncertainty, from structured product pricing and volatility forecasting to synthetic time-series generation using GANs and fractal differentiation.
Currently completing an MSc in Mathematical Trading and Finance at Bayes Business School. President of the Quantitative Finance Society. Recent work includes leading the Deutsche Bank Quant Challenge, where we replicated and presented systematic strategies under real-world constraints.
This repository hosts code, documentation, and models across quant research projects, with an emphasis on clarity, robustness, and economic intuition. Expect stochastic processes, QuantLib experiments, econometric forecasting, and the occasional Bayesian detour.
- Regime-aware systematic strategies across equity market-neutral, trend-following, global macro, and fixed income RV
- Quantitative model design and testing under structural constraints
- Cross-disciplinary methods for inference, robustness, and decision-making
| Project | Summary |
|---|---|
| Risk Analysis | Backtested six VaR models; proposed Expected Shortfall for tail-risk resilience. |
| Structured Bond Valuation | Priced and hedged a BNP Paribas structured product in QuantLib; neutralised DV01 using swaps and CDS. |
| Adjusted Momentum Strategy | Replicated Lou & Polk’s comomentum model; found no performance improvement over baseline. |
| Portfolio Forecasting | EGARCH-based allocation model; outperformed FTSE benchmark over ten-year backtest. |
| Film Clustering | PCA and clustering on IMDB dataset; benchmarked against LLM-generated pipeline. |
| Model Visualisation | Shiny app for exploring tree-based models; included SHAP visualisation and pruning. |
Python, MATLAB, QuantLib
Time-series modelling, backtesting, unsupervised learning, portfolio optimisation