What I do
I do forensic data analysis. When two systems disagree, a metric moves and no decision explains it, or a definition changed quietly three years ago, I trace the figure back through whatever produced it and establish what the records can actually support.
The tools and techniques I reach for when I take a question apart. Data wrangling, modelling, and the dashboards and writing that make the findings usable.
Data wrangling, automation and analytics pipelines.
Predictive and classification models with scikit-learn.
Neural networks with TensorFlow and PyTorch for complex patterns.
Interactive charts and visual storytelling in Plotly and Matplotlib.
Tableau and Power BI dashboards that turn data into decisions.
Reliable pipelines and transformations that hold up in production.
Modelling and querying structured and semi-structured data.
Shipping data apps and models to AWS, DigitalOcean and Render.
Interactive dashboards in Dash, Streamlit and Flask.
Hypothesis testing, regression, and inferential modelling.
Turning complex findings into clear decisions people act on.
Automating recurring work with Airflow, Prefect and cron.
A short record of problems traced back to what was actually causing them. Full write-ups on the projects page.
Project 2025
The used car market in the US is massive—we're talking over $300 billion. But here's the thing: predicting car prices isn't as straightforward as you might think. There are tons of variables at play, and understanding which ones actually matter can make or break a pricing model.
Project 2025
A multi-location shoe retailer was experiencing declining sales due to chronic stockouts in popular sizes, while excess inventory sat unsold. I developed a statistical inventory optimization system that increased sales by 18% in the first year, reversing the company's decline.
Project 2025
Every year, millions of students enroll in college, yet approximately 40% don't complete their degrees. With such high attrition rates, universities desperately need better ways to predict student success. But can a single test score really tell us who will thrive in higher education?
Essays, reviews and field notes on how numbers get used — and how they get used wrongly. The full archive is at the blog.
ESSAY Sep 29, 2026
For the better part of a decade, the world has watched the dawn of artificial intelligence reshape the technological landscape. Companies such as OpenAI, Anthropic, and Google have been at the forefront of this transformation, developing…
ESSAY Sep 18, 2026
No model hits the nail on the head all the time. It is just not possible. It can predict something with a certain level of confidence. It is better than perception. At any point, the predictions could be wrong. To determine the valid…
FIELD NOTE Sep 10, 2026
Machine learning, a form or artificial intelligence, has been used for many years to help with prediction by analysing historical data, recognize patterns, and forecast future outcomes.
ESSAY Sep 04, 2026
Most data science projects fail. And when I say most, I mean 90% of them. More concerning is that only 20% of analytics insights deliver business outcomes.
ESSAY Aug 27, 2026
AI has created a world where people with no knowledge have suddenly become a subject matter experts.
ESSAY Aug 20, 2026
The answer has been long sought by more than scientists and doctors. In fact, the first person who had the idea to record death was neither a scientist or medical doctor. It was a statistian: John Graunt
I learned to separate what evidence shows from what it suggests in roles where being confidently wrong carried a cost. I have a master's in journalism and communications, and I am finishing a doctorate in data science on how findings get communicated.
The writing is not a byproduct of the analysis. It is where the analysis becomes real, and it gets the same scrutiny.
