Offrly Sale Valuation Accuracy Report (2026)

How accurate is Offrly's sale valuation? Each valuation we publish gets compared, after the fact, to the actual sold price recorded in HM Land Registry data. We publish the curated pair set and the metrics — the good and the bad.

Updated 2026-04-29

How we measure accuracy

Offrly's accuracy figures are computed against HM Land Registry Price Paid Data — the authoritative record of every residential property transaction in England and Wales, published monthly under the Open Government Licence.

This is a prediction-vs-outcome report rather than a synthetic back-test. Each figure traces back to a real Offrly prediction and a real HMLR sold-price row:

Every Offrly sale valuation is recorded with its postcode, predicted price and timestamp.
When HMLR publishes its monthly sold-price update, candidate matches surface where a logged valuation's full postcode shows up with a sold date after the valuation was made.
An Offrly admin reviews each candidate against available context — the full address when the user supplied a listing URL, property type, sold-price plausibility — and confirms the right pairing.
Only confirmed pairs feed the metrics on this page: hit rate within ±10% and ±20%, MdAPE, MAE, RMSE and bias.

What this number means, and what it doesn't. Hit rate within ±10% is the share of Offrly estimates that land within 10% of the actual sold price. A 60% hit rate means 6 in 10 estimates were within ±10% — comparable to where mainstream automated valuation models (the postcode-average tools most free portals run on) typically land for UK homes. The conceptual difference matters: a traditional automated valuation model gives every house on the same street roughly the same number, because it can only see beds, postcode and broad type — not what the home actually looks like. Offrly's regression reads each comparable's photos for condition and garden quality the way a human analyst would, and resolves price at the street level rather than the postcode — so two homes on the same road that look very different get priced very differently. A valuation is still a market estimate, not a guaranteed sale price. For probate, mortgage or insurance purposes, use a RICS-qualified surveyor.

What's in the report, transparently

Scope: sale valuations only. Rentals are not included — there's no public sold-price equivalent for rentals to pair them against.
Ground truth: HM Land Registry Price Paid Data — every arms-length freehold and most leasehold residential sales in England and Wales.
Licence: Open Government Licence v3.0 — reusable, citable.
Sample: 0 curated pairs of (Offrly prediction, HMLR sold price), all on the same property.
Leakage controls: by construction, every prediction was made strictly before its matched HMLR sold date — predictions never see future sold prices.
Update cadence: the page recomputes on every load from the current curated pair set; the curated set grows as HMLR publishes monthly updates.

How we compare to the rest of the market

Mainstream automated valuation models — the postcode-average tools most free portals run on — publish hit-rate-within-±10% figures broadly in the 60–70% band. Offrly's differentiator isn't just the point estimate, it's the model architecture: a photo-aware AI that reads each comparable's photos for condition and garden quality the way a human analyst would, paired with a hyperlocal regression that resolves prices down to the street rather than the postcode. Free, no signup, with the methodology and the curated pair set both auditable on this page.

All accuracy claims age quickly as the market moves. As fresh HMLR data lands and new pairs are curated, the figures here update.

Try a free valuation

See for yourself how close Offrly gets. No signup, no email, about 30 seconds.

Run a free valuation →

Frequently asked questions

What does 'hit rate within ±10%' mean?

It's the share of Offrly sale estimates that land within 10% of the actual sold price in our curated pair set. A 60% hit rate means 6 in 10 estimates were within ±10% — an industry-standard way of measuring how close an automated valuation model gets to the true price.

How is the pair set curated?

Every Offrly sale valuation is logged with its postcode and predicted price. When HM Land Registry publishes its monthly sold-price drop, an admin reviews each candidate match (same postcode, sold after the valuation date) and confirms the right pairing using the available context — full address when the user supplied a public listing URL, property type, sold-price plausibility. Only confirmed pairs feed the figures here.

Does this cover rentals?

No. The accuracy report is for sale valuations only. There is no public sold-price equivalent for rentals, so we cannot publish a comparable rental accuracy figure honestly.

Is this the only accuracy number Offrly publishes?

Yes. We don't cite model internals, proprietary benchmarks, or cherry-picked cases. The only public accuracy claim Offrly makes is this page, sourced from primary HM Land Registry data.

Why should I trust these figures more than a marketing claim?

Because the ground truth is HM Land Registry, published under the Open Government Licence — and our methodology is described in full above. Each figure on this page traces back to a specific Offrly prediction and a specific HMLR sold-price row.

Should I use an Offrly valuation instead of a surveyor?

No. Offrly estimates are indicative market guidance. For probate, mortgage, insurance or tax-binding figures, use a RICS-qualified surveyor. Offrly is for orientation, negotiation and informal decision-making — not for binding purposes.

Source: HM Land Registry Price Paid Data, licensed under Open Government Licence v3.0. Offrly estimates are indicative market guidance — not regulated valuations and not financial, tax or legal advice.