Hi, I’m David Bates — a Physics graduate from Imperial College London with a strong interest in sports analytics, machine learning, and turning complex datasets into meaningful, actionable insights. I enjoy applying statistical modelling and predictive techniques to real-world problems, particularly in sport, where data-driven thinking can uncover trends, challenge assumptions, and improve decision-making.
Some of my favourite projects so far have been in American football and snooker, where I’ve built tools that combine rigorous analysis with intuitive visualisation:
- 🏈 A custom Elo rating system that tracks and predicts NFL team performance, adjusting dynamically for factors such as home-field advantage and margin of victory.
- 🎯 DeepCue, a machine learning model that forecasts snooker match outcomes by blending historical performance, matchup dynamics, and feature engineering to capture subtle influences on results.
Beyond sports, I’ve explored large and varied datasets across different fields. My Master’s thesis focused on analysing satellite climate and emissions data, applying statistical inference to understand environmental trends. I’ve also designed automated reporting pipelines and analytical workflows using Python, SQL, and Excel VBA — helping to transform raw, unstructured information into clear and actionable reports.
Right now, I’m looking for new opportunities where I can bring this analytical mindset to sports, finance, or technology — ideally in a role that values curiosity, creativity, and a willingness to experiment. I’m particularly interested in collaborating with others, whether that’s co-developing models, exploring new datasets, or simply exchanging ideas over coffee.
If you share an interest in data-driven problem solving — especially where sport and technology meet — I’d love to connect and talk.