Leeds, England, United Kingdom
Data scientist with 6 years of experience applying statistical modelling and analytical techniques to derive actionable insights from multi-dimensional data. Experienced in turning complex information into evidence-based recommendations for policy and strategic decision-making. Publications and analyses produced in collaboration with the Scottish Government and the Mental Health Foundation (MHF), including work on the adult mental health impacts of child payment policy used by the MHF to lobby officials ahead of the October 2024 budget. Strong in statistical modelling, data visualisation, and communicating results to technical and non-technical audiences.
Architected and deployed Python/R microsimulation pipelines, managing and analyzing longitudinal datasets of 600k+ data points (UKHLS, 12 waves) to automate policy projections. Led end-to-end model development for large-scale synthetic population simulations, delivering evidence based projections used by the Scottish Government and Public Health Scotland. Developed data engineering workflows to handle multi-dimensional survey data, ensuring technical excellence and model reproducibility. Influenced senior stakeholders at the Mental Health Foundation, the Scottish Government, and GMCA, translating complex statistical outputs into clear strategic recommendations for national and regional level policy.
Engineered real-time data assimilation systems for agent-based simulations (ABM), utilizing probabilistic programming (Keanu) and Java to process streaming data sources. Led the technical adaptation of a US-based health microsimulation framework for the UK market, building custom data pipelines to integrate national English longitudinal datasets. Collaborated internationally with researchers at the University of Southern California (USC), presenting technical findings on simulation methodology. Received a full-time offer to continue as a Research Assistant following successful delivery of core project milestones.