I spent my early career in finance and banking, working close to markets, pricing and risk. Now I’m pivoting into machine learning and deep learning — applying the same domain instinct, but with code, data, and models. The four projects below are how I’m proving the move out, end to end: from raw data to trained models to live demos.
My finance background gave me a strong feel for time series, risk, pricing, and noisy real-world data — the exact problems machine learning is built for. I'm self-teaching in public: every project ships with code, a README, and a live demo, so the work speaks for itself.
Stack I work with day to day: Python, PyTorch, scikit-learn, XGBoost / CatBoost, FastAPI, and plain HTML/CSS for demos.
Quantitative deep-dive on 12 equities: Black–Scholes option pricing, Sharpe ratio, probability of loss, and derivative-based summary statistics. The math foundation behind the ML projects above.
View project →Supervised regression on the German real-estate market. Feature engineering, model tuning, and an iteration log showing how the model improved version by version — not just the final number.
View project →Transaction-level retail modelling with gradient-boosted trees. Three model iterations, each documented with what changed and why — the same iterative loop I follow on every project.
View project →End-to-end deep learning system: ingest equity price history, train sequence models (LSTM and Transformer), serve predictions through a FastAPI backend, and visualise them in a live dashboard.
View project →