Economics & Actuarial Science graduate | Incoming Actuarial Consultant at Willis Towers Watson | Quantitative Finance & Data Science enthusiast
I build quantitative tools because I genuinely enjoy it. My projects sit at the intersection of financial modelling, actuarial science, and applied machine learning — built in Python, deployed, and published here.
A Python-based financial valuation tool that ingests a company's 10-K PDF or stock ticker and automatically produces:
- DCF valuation with WACC calculation
- Comparable companies analysis benchmarked by revenue and industry
- LBO model with financing advice
Works for both public and private companies — just upload the 10-K.
🔍 SKEW
A free NLP-based economic fact verifier. Paste a claim, SKEW runs statistical tests against source documents and tells you whether it holds up. Built so anyone can verify economic facts they see online — quickly and for free.
A comprehensive actuarial pricing engine for non-life insurance, deployed as a Streamlit app. Covers:
- 15+ discrete claim frequency distributions including Poisson, Negative Binomial, Zero-Inflated, Hurdle, Panjer class, and Poisson-Binomial (implemented from scratch)
- Continuous claim severity distributions including Lognormal, Gamma, Weibull, Pareto, and Burr
- Ruin theory calculations for solvency analysis
- Libraries: NumPy, SciPy, Streamlit
🔗 Live app
Options pricing and risk management tool built as part of my Derivatives with Coding module (78%):
- Calibrated Black-Scholes implied volatility surface and SVI local volatility model
- Simulated 5,000 Monte Carlo paths
- Applied daily delta hedging strategy reducing 99% VaR by 55%
- Libraries: Pandas, NumPy, Scipy, Matplotlib
Two-stock portfolio optimiser applying Modern Portfolio Theory and Sharpe ratio maximisation.
Actuarial pricing model for life insurance policies built in Python, applying mortality tables and discounting frameworks.
languages = ["Python", "R", "Stata"]
libraries = ["Pandas", "NumPy", "Scipy", "Statsmodels", "Matplotlib",
"Scikit-learn", "yfinance", "Beautiful Soup", "pdfplumber"]
finance = ["DCF", "LBO", "Comparable Companies Analysis", "Options Pricing",
"BSM", "SVI Local Vol", "Monte Carlo Simulation", "Delta Hedging",
"Claim Frequency Modelling", "Ruin Theory"]
tools = ["Excel", "PowerPoint", "Bloomberg Market Concepts Certificate",
"Streamlit"]
learning = ["Reinforcement Learning (UCL lectures)", "NLP", "Applied ML"]