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 2026
An audit of 497,882 voting-machine logs from Brazil's 25 October 2026 runoff: where the court-ordered two-hour extension actually happened, and whether it tracked political lean.
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.
Essays, reviews and field notes on how numbers get used — and how they get used wrongly. The full archive is at the blog.
ESSAY Oct 26, 2026
Cyberattack has grown exponentially in the healthcare industry. Data science can help with the detection and prevention of data breach.
ESSAY Oct 19, 2026
Most dashboards are dead on arrival. While the causes depend on multiple factors, these mistakes don't help the cause.
ESSAY Oct 15, 2026
The world is filled with rivalries. Different school of thoughts that propel ideas forward. Distinct ideologies that changed the course of a nation or a group of people. Elizabeth I and Mary Queen of Scots. Hamilton and Jefferson. Real …
FIELD NOTE Oct 08, 2026
Data visualization has become part of our daily lives. All you have to do is login to an platform and you are immediately directed to a dashboard with fancy graphs. Our eyes have become so accustumed to seeing these diagrams that unless on…
ESSAY Oct 01, 2026
Working in this industry for well over a decade, the question, which is better, R or Python, comes up every so often. Python has always been my go-to language, and for many years that’s what I would say. But experience has a way of chang…
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…
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.
