Introducing InferSol: Machine Learning Consultancy in Cambridge
At InferSol, we help businesses make better decisions by developing and applying rigorous inference pipelines for their data.
Surrogate Modelling and Bayesian Inference for real business and research problems
We are a Cambridge-based consultancy specialising in building fast surrogate models for expensive simulations and performing principled Bayesian Inference. We work closely with businesses and researchers to build practical, tailored solutions for their modelling needs and unlock insights from their data.
What we do
Our services
We offer a range of advice and services to help you get the most from your data.
Surrogate Modelling
We build state-of-the-art fast and accurate surrogate models for complex and expensive simulations - making research possible.
Bayesian Inference
We apply rigorous statistical methods, rooted in Bayesian inference, to extract clear, actionable insights and help you ask better questions of your data.
Who we are
Cambridge expertise, applied to your data
Led by Harry Bevins
Research Fellow at the University of Cambridge who gained his PhD in Physics in 2023. Specialist in Bayesian inference, surrogate modelling, and statistical analysis.Research background
Our approach is grounded in years of research at the University of Cambridge, applying Bayesian inference and surrogate modelling to real-world problems in astrophysics and cosmology.
Practical focus
We favour interpretable, well-validated models over black-box complexity, and work closely with clients throughout rather than just handing over a report at the end.
Problem-first approach
Every engagement starts with understanding the business or research problem before any modelling. We help you ask better questions of your data, not just answer the ones you already have.
News & Projects
View all posts »Insights, case studies, and updates from InferSol, where we share what we've been working on and what we've learned along the way.
Have a data problem?
If you're not sure how to approach it, we'd be happy to have an initial conversation — no commitment required.