THE RECEIPTS

WE SHOW OUR WORK.

Every prediction goes on the record. Here is how close our predicted sale prices land on homes that have since sold, for the whole region and for every place in it.
2.2%
Typical gap between our predicted sale price and the actual sale price.
Measured on 26,875 homes we predicted before they sold. About 8 in 10 landed within 5 percent of the final price. Checked against sales through September 7, 2026.

What this number is

When a home is listed, First Access Signals records a predicted sale price for it. When that home later sells, we compare the prediction to the real selling price. The number above is the median gap across those homes: half of our predicted prices land closer than that, and half land further.

Every place, not just the average

One number for a region this large hides more than it tells. Our estimates are closer in some cities than others, and in a few places they lean consistently one way. So the table below breaks the same record out by city and by postal area, with the number of homes behind every figure.
Nothing is left out. Places with only a handful of graded sales are here too, marked, because a breakdown that quietly drops its smallest rows stops adding up to the total above it. The counts in the table sum to the count in the headline.
Loading the place by place record.

How to read the lean

The last column is the direction we tend to miss in, not the size of the miss. A place reading low is one where our estimate has usually come in under the eventual sale price. Where we cannot tell a direction apart from ordinary scatter, it reads level rather than showing a number we cannot stand behind, and the range under each row says how confident that is.
We watch this ourselves. A place whose lean becomes both real and large is treated as something to fix in the model, and until it is fixed we stop showing that place a headline accuracy figure anywhere else in the app.

See it home by home

We do not just publish these numbers. On a closed listing, the app shows what we predicted next to what the home actually sold for, so you can check us one sale at a time. Browse listings.

How we measure it

We use the median absolute percentage gap, the standard accuracy measure for home-value estimates, and we leave out any home that was used to build the model, so every figure here is out-of-sample, measured on homes the model had not seen. We grade the last estimate we published while the home was still for sale, against the price it actually sold for. The full methodology, including the chance-of-selling side of the Signal, is on the methodology page.

Who can see what

The accuracy figures on this page are public, for the region and for every place in it. The price a specific home sold for is reserved for registered consumers, because board rules treat closed sale prices as members-only. Create a free account to see the per-home comparisons.