Accuracy
Live metrics from walk-forward backtesting against actual Land Registry sale prices. No cherry-picking. No simulated data. These are real predictions vs real outcomes.
Reading the metrics
PE10 (Percentage within 10%)
The proportion of valuations where the model's estimate fell within 10% of the actual sale price. This is the industry-standard accuracy metric for automated valuation models. A PE10 above 80% is considered strong performance for a national AVM.
MdAPE (Median Absolute Percentage Error)
The median percentage by which the model's estimate differs from the actual sale price. Using the median rather than the mean prevents outliers from distorting the figure. Lower is better.
Test count
The number of properties used in the backtest holdout set. A larger test set produces more statistically robust accuracy measurements. We use walk-forward validation: the model is trained on historical data and tested on subsequent sales it has never seen.
Regional breakdown
Model performance varies by region. Dense urban markets with high transaction volumes typically produce stronger results than rural areas with fewer comparables.
| Region | PE10 | MdAPE | Test Properties |
|---|---|---|---|
| East Midlands | 63.8% | 7.1% | 21,132 |
| East of England | 64.2% | 7.1% | 30,478 |
| London | 60.5% | 7.8% | 37,467 |
| North East | 52.2% | 9.4% | 14,595 |
| North West | 56.2% | 8.5% | 41,154 |
| South East | 63.7% | 7.2% | 45,149 |
| South West | 62.4% | 7.4% | 33,038 |
| Unknown | 50.0% | 10.1% | 100 |
| Wales | 56.2% | 8.6% | 14,770 |
| West Midlands | 61.1% | 7.6% | 25,190 |
| Yorkshire | 56.5% | 8.5% | 31,967 |
Confidence tiers
Every valuation is assigned a confidence tier based on the availability of comparable evidence, feature completeness, and model prediction uncertainty. This tells you how much weight to place on the estimate.
Tier 1 — High Confidence
Strong comparable evidence, standard property type, active local market. The prediction interval is narrow and the model has high certainty. Suitable for lending and investment decisions with appropriate due diligence.
Tier 2 — Medium Confidence
Reasonable comparable evidence with some gaps. The prediction interval is moderate. Useful as a price indication but consider supplementing with local market knowledge.
Tier 3 — Low Confidence
Limited comparable evidence, unusual property, thin market, or significant data gaps. The prediction interval is wide. Treat as indicative only — a formal valuation is recommended.
Want the technical detail?
Our methodology page explains the model architecture, feature engineering, validation approach, and compliance framework in full.
Read the methodology