About Me

My path to data science came from a passion for quantitative analysis and having the capability of addressing valuable problems. Starting off with a background in Medical Physics and Bioengineering, I first applied these abilities in the HealthTech sector, conducting detailed data analysis, designing predictive models, and analysing clinical trial outcomes – gaining experience in pulling useful information from nuanced data.

Driven by a necessity to develop more comprehensive and scalable solutions, I grew my expertise along the entire data lifecycle, from exploratory data analysis to deployment. This encompassed learning Machine Learning Operations (MLOps) patterns – such as cloud-based data pipelines (GCP) and model monitoring. I also have expertise in advanced techniques for use on a range of issues, including geospatial analysis to discover spatial patterns and interpretable ML (SHAP) to build trust in predictions.

While I do have a specific interest and great experience in applying data analysis and machine learning in environmental science and healthcare, my interest is broader in applying data effectively to resolve challenging problems wherever they are to be found. My rule of thumb is to develop solutions – from deep analysis, modelling, or dashboards – that are technically sound, efficient, readable, and actionable. I keep exploring deeper techniques, including causal inference (PSM) and LLMs/RAG, to enhance data analysis capability and unlock wider understanding in various application domains.