Innovating Environmental & Healthcare Solutions Through Data Science

Applying machine learning, MLOps, and data analysis techniques to solve complex challenges in environmental science and healthcare.

View Projects Learn More About Me

Featured Projects

Environmental Justice Analysis

Built an end-to-end geospatial & ML pipeline (Python, GeoPandas, Scikit-learn, PySAL) applying spatial statistics, clustering, and predictive modelling to analyse environmental justice disparities in the UK.

Geospatial Python Data Analysis Social Impact

Code

MIMIC MLOps Pipeline

Engineered an MLOps pipeline PoC (Python, Scikit-learn, MLflow, Docker, FastAPI) using MIMIC data for predicting hospital readmissions, focusing on reproducibility, experiment tracking, and deployment.

Healthcare Readmission Prediction Imbalance Handling SHAP

Code

Online Retail CLV Dashboard

Analysed the classic Online Retail dataset (2010-2011) using RFM segmentation and probabilistic models (BG/NBD, Gamma-Gamma) to predict Customer Lifetime Value. Includes an interactive dashboard.

Dashboard CLV Streamlit Data Viz

Code

Skills & Expertise

Languages & Databases

Python (Pandas, Scikit-learn) SQL (BigQuery) NumPy Statsmodels

ML & Data Analysis

Predictive Modeling (Regression, Classification) Clustering Feature Engineering Model Evaluation (SHAP) A/B Testing

Geospatial Analysis

GeoPandas PySAL Spatial Statistics QGIS

Cloud & MLOps

GCP (BigQuery, Storage) MLflow Docker FastAPI CI/CD (GitHub Actions) Monitoring Principles

Visualisation & BI

Plotly Streamlit Power BI Tableau Matplotlib/Seaborn

Advanced Techniques

Interpretable ML (SHAP) Causal Inference (PSM) Time-Series LLM/RAG Exploration

About Me

Driven by a passion for using data to understand and improve the world around us. Currently exploring intersections between technology, environmental sustainability, and healthcare equity.

Read My Full Story →

Let's Connect

Interested in collaborating or discussing potential opportunities? I'd love to hear from you.

Get In Touch