ForceSight

What it does

ForceSight predicts how a police force is likely to score in its next HMICFRS PEEL inspection — the Effectiveness, Efficiency and Legitimacy ratings used to judge force performance — using a model trained on historical Home Office data rather than waiting for the inspection itself. A dashboard, styled as a GOV.UK prototype service, lets a user switch between a national overview and a single force’s detail view, surfacing the key factors behind that force’s predicted rating.

How it works

A Random Forest model is trained separately for each of the three PEEL pillars on a cleaned, feature-engineered dataset of force-level indicators. A feature-analysis pass over the trained models identifies which factors matter most for each pillar, turning raw model output into something a policy audience can act on rather than a black box. The frontend is a static GOV.UK-styled dashboard that reads the model’s outputs and factor rankings and renders them per force.

The interesting problem

TODO (James) — what was genuinely hard here: likely candidates are the feature engineering/data cleaning from messy multi-year Home Office data, or getting a Random Forest’s feature importances into a form a non-technical audience could actually use.

Stack and why

A Random Forest was chosen over more opaque models for its built-in feature importances — for a policy-facing prototype, being able to explain why a force scored as predicted mattered as much as the prediction itself. The frontend deliberately mimics the GOV.UK Design System so the prototype reads as a plausible real government service rather than a generic hackathon demo.

What I would do differently

TODO (James) — short, in your own words.