I don't really trust a model
until I can watch it run.
So this portfolio is built around that habit. By day I build statistical-arbitrage strategies for European power and gas at Engie Global Markets. The rest of these pages are quant ideas I rebuilt from scratch and put live in the browser, so you can poke at them rather than take my word for it: order books and Hawkes flow, efficient frontiers on real market data, option pricing, a bit of reinforcement learning. The full CV-style story is on the About page.
From market microstructure to free-boundary pricing, each topic comes with a model you can run and break directly in the browser - order books and Hawkes flow, efficient frontiers on live S&P 500 data, volatility smiles, neural nets trained on the spot, and a Q-learning agent solving mazes.
Order Flow: From Poisson to Hawkes
A live limit order book with a trading ladder, driven by three models of order flow: homogeneous Poisson, a time-varying Poisson fitted to the intraday U-shape by thinning, and a self-exciting Hawkes process with MLE calibration.
Markowitz in Practice
The efficient frontier built live on ten S&P 500 stocks - min-variance vs max-Sharpe out of sample - and Random Matrix Theory eigenvalue clipping to fix the covariance matrix that betrays the optimiser.
Monte Carlo & the Volatility Smile
Euler vs Milstein strong convergence measured live, Heston Monte Carlo with full-truncation, and implied-volatility smiles backed out by bisection - drag ρ and watch the equity skew appear.
Optimization Under Constraints
Gradient descent with a live step-size stability limit, plus constrained solvers (projection, penalisation, Uzawa) on a 2-D problem - the KKT machinery behind Markowitz and support vector machines.
Free Boundaries & Exotic Pricing
Pricing American and Bermudan options by solving the Black-Scholes PDE with finite differences - early-exercise boundaries, and the same machinery applied to Bermudan swaptions.
Deep Learning in Finance
An autoencoder trained live in your browser to compress the cross-section of returns and flag anomalous days, plus a tour of CNN roughness estimation, no-arbitrage pricing networks, LSTMs and GANs for synthetic markets.
Q-Learning in a Maze
A tabular Q-learning agent trained live on a freshly generated maze: watch the value function flood backwards from the goal and the greedy policy snap onto the shortest path.