Projects
Technical case studies built around context, method, selected implementation, evidence, limitations and what I learned. GitHub holds the complete source; these pages explain why the work was built the way it was.
A comparative medical-classification exercise using multiple algorithms, standardised cellular features and confusion-matrix analysis.
A FashionMNIST computer-vision experiment comparing CNN architectures, with a TinyVGG-inspired model and detailed error inspection.
A graph-based proof-of-concept simulation that translates a biological cross-correction hypothesis into diffusion, decay, exposure and rescue-threshold dynamics.
A country-year macroeconomic risk experiment combining Rust feature engineering, Python modelling and a Streamlit scenario dashboard.
I used K-Means clustering and PCA to turn high-dimensional credit-card behaviour into an interpretable customer-segmentation exercise.
A bank-customer churn classifier built with an ANN after encoding mixed categorical and numerical features into one training pipeline.
A classification comparison on social-network advertising data, using age and salary to predict purchase behaviour and visualise decision boundaries.
An exploratory World Bank analysis linking birth rate, internet use and life expectancy across countries, regions and income groups.
A small-regression comparison exploring how linear, polynomial, SVR, tree and ensemble models represent non-linear salary progression by position level.
An exploratory R analysis of top-grossing US films, focusing on release timing, genre, studio and domestic gross patterns.
An R-based profitability analysis that calculates profit after tax and profit margin, then visualises monthly financial performance.
A portfolio-allocation and risk-analysis exercise using normalised stock prices, random weights, daily returns and the Sharpe ratio.
A multiple-linear-regression pipeline predicting startup profit from spending variables and encoded location information.
An exploratory stock-market analysis of normalised prices, daily returns, correlations and volatility across multiple equities and the S&P 500.
A Tesla next-day price forecasting experiment using scaled price/volume inputs and a stacked LSTM network.
A regularised stock-price regression experiment using historical price/volume features, held-out testing and cross-validation.
A CAPM-focused analysis estimating stock beta and alpha against the S&P 500 and using those coefficients to explore expected return.