Forecast evaluation study reveals persistent overestimation in prison population projections, indicating that simple no-change models outperform official forecasts.
Walkforward Research Paper 2026/02. Version 1.0, September 2026. Eighteen editions of the Ministry of Justice prison population projections since 2008, with every central projection scored against what happened at every horizon. The projections have been too high at every horizon, and a forecaster who assumed no change would have beaten them on identical targets. Code at github.com/walkforwardresearch/prisoncap.
No takes yet. Share an insight, caveat, or question.
Hamish Paton (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: