About ReadingSignal
ReadingSignal is an independent UK election forecaster built around three principles:
- Show the working. Every projection comes from a transparent model pipeline. No black boxes.
- Be honest about uncertainty. Confidence intervals are wide because the underlying reality is uncertain. Forecasts are probability distributions, not predictions.
- Go beyond uniform swing. Averaging polls and applying one national swing to every seat misses how unevenly votes are actually distributed. The model converts vote intention into seats using demographic structure and vote-switching dynamics, with empirically calibrated geographic variance.
Where it's heading: the goal is a genuinely multi-signal forecast — combining polling with independent sources like prediction markets, leader approval, and economic fundamentals. Independent signals with uncorrelated errors, properly combined, should beat any single one. That's the roadmap.
The site covers UK general elections, devolved elections (Scotland and Wales), and major local election cycles.
Current calibration
The model (v2.4) was recalibrated in late May 2026 against the local election results and the YouGov / More in Common / Electoral Calculus MRPs, using a multi-party iterative-proportional-fitting (IPF) calibration that fits a full 2024→2026 vote-transition matrix to the polling targets. v2.4 reconciles the simulation to the underlying decomposition: the headline forecast and the methodology's central scenario are now one coherent model rather than two that disagreed. The headline is Reform as the largest party, with no single party near a majority.
The forecast — Monte Carlo mean, 2,000 simulations
Ref 217 · Lab 128 · Con 120 · LD 93 · SNP 41 · Green 17 · PC 7
P(Reform largest) = 71% · P(hung parliament) = 100%
The central deterministic decomposition — the seat-by-seat projection before simulation — now agrees with the forecast within sampling spread (Lab 126 · Ref 225 · Con 115 · LD 94 · Green 14). The one material gap is Reform: the decomposition gives ~225, the simulated mean ~217. That is the expected first-past-the-post effect, not a calibration disagreement — symmetric per-seat polling noise costs a fragmented plurality leader more seats than it gains across the many three- and four-way marginals where Reform leads narrowly, and those seats scatter to the runners-up.
Being explicit about where this lands against the MRPs: Labour (128) sits below the published consensus floor (YouGov 138 / More in Common 165), and Green (17) sits above the MRP range (4–7). We publish what the model says rather than nudging it toward the MRPs. The Labour gap is a seat-conversion question in the Red Wall Labour–Reform marginals; the Green number reflects the model reading Green as competitive in more seats than the MRPs award. Both are stated, not smoothed.
One vote-share residual remains on the checklist, separate from the seat reconciliation: Labour's national vote share still projects about 2pp above its turnout-adjusted polling target. It is a publicly checkable number and it is queued for the next calibration pass. The model on the site is materially better calibrated than the previous version, but not finished.
Who built it
ReadingSignal is built and maintained by Jim Moodie. Jim spent 7.5 years as COO of Prolific, the online research platform used worldwide by academic researchers and social scientists — work that involved many of the same methodological challenges pollsters face: building representative samples, controlling for response biases, and assessing data quality at scale.
He has a long-standing interest in forecasting and prediction markets. ReadingSignal is one of several prediction modelling projects he's working on. More background at jahm.me.
Get in touch
Questions, corrections, or methodological challenges welcome via Twitter/X: @yojimbo23.