Quantitative Finance & Data Science profile focused on applying mathematics, statistics, programming and AI to problems in finance, banking, risk analytics and derivatives pricing.
- Quantitative Finance
- Risk & Banking Analytics
- Data Science / Machine Learning
- Python for analysis, modelling and prototyping
- C++ for numerical methods and performance
- SQL, Excel and Power BI for reporting
- Applied AI / LLMs in finance
| Status | Project | Focus |
|---|---|---|
| Completed | Regime-Switching Local-Volatility Option Pricing (MSc thesis) | Two-regime local-volatility PDE, finite differences, convergence, American puts, empirical validation and Power BI |
| In progress | Credit Risk Model Validation | PD modelling, challenger models, discrimination, calibration, stability and simplified IFRS 9 ECL |
| Next | Option Pricing: Python vs C++ | Black-Scholes, Monte Carlo, numerical methods and performance comparison |
| Planned | Market Risk: VaR & Expected Shortfall | Historical simulation, Monte Carlo, backtesting and risk reporting |
| Planned | Volatility Forecasting | Time series, GARCH and regime-switching models |
| Planned | Financial RAG Assistant | LLMs, embeddings and financial document analysis |
The goal of this portfolio is to build practical, well-documented projects that connect:
Finance problem
→ data
→ modelling
→ implementation
→ evaluation
→ interpretation
→ communication
Python is used mainly for research, analysis and modelling. C++ is used where numerical performance matters, especially in quant finance.
Python | C++ | SQL | Excel | Power BI | Machine Learning | Quant Finance | Applied AI