A bit about me
A data scientist with a strong quantitative foundation and a practical focus on shipping things that work.
My background is in statistics and mathematics — I did my master's in statistics, then spent a couple of years in quantitative trading before moving into data science. That path gave me a solid foundation in the kind of rigorous, quantitative thinking that underpins good data work.
Since then I've worked in insurtech, and now I consult independently with B2B clients on data and analytics problems. I've built fraud detection models, real-time data pipelines, KPI dashboards, and AI-powered tools — always with a focus on making the output useful to the people who need it.
I like problems that sit at the boundary between technical and business. Getting the math right matters, but so does understanding what someone actually needs to decide, and making sure the analysis helps them get there.
"The most valuable thing you can do at the start of a data project is resist the urge to open a notebook and spend the time instead understanding the problem."
This is something I've learned from experience. Most of the time, the hard part isn't the analysis — it's getting clear on what question is actually worth answering.
Rocking out in Jasper National Park
2025Data Science & Analytics Consultant
Self-Employed
Working with B2B clients across research, marketing, and sales — owning projects end-to-end from scoping and pipeline development through to stakeholder-facing insights and recommendations.
Data Scientist
Insurtech
Built and maintained fraud detection models for insurance clients, working directly with client data structures. Also built data pipelines for processing large extracts, and led client-facing meetings to gather requirements and communicate findings.
Market Analyst
Prop trading
Developed and executed quantitative trading strategies — momentum, pairs trading, trend following — and built a real-time market data pipeline in Python and SQL for high-frequency data ingestion and querying.
A few things I've learned
The part of data science I enjoy most isn't the code — it's the translation. Taking a vague business question, turning it into something you can analyze, and then explaining the result in a way that actually changes what someone does. That's the skill I work hardest at.
Understand the business first
A data project without a clear business question is just computation. I spend real time on scoping before touching the data.
Pipelines before models
The best model on bad or unreliable data is worthless. Getting the data infrastructure right is where most of the value lives.
Communicate the "so what"
Analysis is only useful if someone acts on it. I care about translating technical findings into recommendations that make sense to decision-makers.
Iterate based on feedback
The first version is never the final version. Working closely with stakeholders and adjusting based on what they actually need is how good work gets built.
Want to see the work?