Data systems, end to end — the models, the pipelines that feed them, and the software people actually use.
Sometimes a forecasting model. Sometimes a reporting pipeline nobody wants to own, an internal tool, a dashboard, or a website. The common thread is data that has to be right, and software that has to keep running.
Models
Forecasting, pricing, scoring, simulation. Built against a decision someone actually has to make, validated honestly, documented, and monitored once they are live.
Analytics
Pipelines, metrics and reporting. Data cleaned, every number defined in writing, and the whole thing reproducible — so the answer does not change depending on who ran it.
Software
Dashboards, internal tools, APIs, websites, and the infrastructure underneath them. The software that puts a model, or a number, in front of the people who have to act on it.
Contact
Bring a problem: a dataset nobody can make sense of, a model that needs building or checking, a dashboard, an internal tool, a website.
Get in touch →