How it works

How we value a property and judge the guide

Every report shows its working. This page explains each part: where the number comes from, how the "why" amounts are calculated, how the verdict is decided, and how accurate it has been on sales it never saw.

1 · The market value

From an address to a price

1

Find the property

We match the address against the NSW address file (G-NAF) and the Valuer General's sales records. Small typos in the street or suburb are corrected, and the report tells you when that happens. The match gives us the exact map position and, if the property has sold before, its last sale.

2

Build its profile

The model looks at 25 facts about the property:

  • Postcode price level: the typical price for this type of property in its postcode in the current year, from every sale in the postcode since 1990.
  • Last sale: how far above or below the postcode level it sold last time, what that price is worth today after local growth, and how long ago it was.
  • Street and neighbourhood: how far past sales on the same street, within about 500 m, within about 2 km and in the suburb ran above or below the postcode level. Streets with only a few sales are pulled towards zero, so one unusual sale can't swing them.
  • Location: map position, distance to the Sydney CBD and distance to the coast.
  • Size: land area for houses; strata lot area (including a car space) for apartments.
  • Type and zoning: house or apartment, and the land zoning.
3

Run the model

The model is a LightGBM gradient-boosted tree model: 1,250 small decision trees. It starts from the postcode price level, and each tree adds a small correction based on the property's profile. It learned those corrections from 3,851,833 cleaned NSW residential sales from 1990 to November 2026. Non-market sales are left out of training: prices more than four times above or below the postcode level, and properties resold within 90 days at a very different price.

4

Price it as at today

The result is the estimated sale price today, rounded to the nearest $1,000. The calculation runs in your browser: the address you type isn't sent anywhere.

What the model relies on most

Share of the model's decisions driven by each kind of information (LightGBM split gain):

Street, suburb and nearby sales
44%
This property's last sale
37%
Postcode and market timing
10%
Size
6%
Type and zoning
2%
Exact location
2%

The street and neighbourhood, and the property's own last sale, do most of the work. That's why estimates are more reliable for properties that have sold before.

2 · Why this value

How the "why" amounts are calculated

Each line in "What moves the price" answers one question: how much would the estimate change if this property were typical for its area in that one respect? We run the model again with that single input swapped for the typical value, and the difference is the dollar amount.

Street, location and size are measured as if the property had no previous sale, because its own sale already reflects its street and position and would hide their effect. The amounts don't add up to the estimate; each shows one factor on its own.

Example: 9/162 Gardeners Rd, Kingsford ($890,000). It last sold for $828,888 in Feb 2024, 7% below the area's going rate then, so the last sale takes $28,301 off. Gardeners Rd sales have run 12% below the postcode norm, partly offset by nearby streets, which takes $44,577 off. It's 0.8 km farther from the coast than usual and 3% smaller, but the model's trees don't react to differences that small, so both show No effect.

Two messages you may see:

3 · The verdict

How the price guide is judged

We compare the middle of the price guide (for "$800k – $850k", that's $825k) with our estimate. Whether a gap is big depends on how accurate the estimate usually is, so the bands come from real results: how far actual sale prices landed from our estimates on 16,308 recent sales the model never saw.

middle half of sales 5.3% of sales 0.7% of sales 1.2% of sales 1.6% of sales 2.0% of sales 3.2% of sales 5.1% of sales 7.7% of sales 10.9% of sales 14.5% of sales 13.5% of sales 10.6% of sales 7.5% of sales 4.8% of sales 3.1% of sales 2.1% of sales 1.7% of sales 1.0% of sales 0.8% of sales 2.6% of sales ≤ −39% −20% estimate +20% ≥ +65% Actual sale price compared with our estimate

Half of all sales landed between -10% and +9% of the estimate (properties that had sold before). A guide inside that middle half is fairly valued. The further outside it, the stronger the verdict:

VerdictWhere the guide falls among real outcomesSold beforeNo earlier sale
UndervaluedBelow the 10th percentilemore than 21% belowmore than 30% below
Possibly undervalued10th–25th percentile10–21% below13–30% below
Fairly valued25th–75th percentile-10% to +9%-13% to +14%
Possibly overvalued75th–90th percentile9–21% above14–33% above
OvervaluedAbove the 90th percentilemore than 21% abovemore than 33% above

Properties with no earlier sale on record have wider bands, because their estimates are less certain. The verdict also tells you how unusual the gap is, for example "only 12% of sales land this far below our estimate".

Example: Gardeners Rd's guide of $800k – $850k has a midpoint 7% below the $890,000 estimate. That's inside the middle half (−10% to +9%), so it's fairly valued.

About low guides

In NSW, guides are often set below the expected sale price to draw buyers, especially at auction. When a guide looks undervalued, the report reminds you of this. Check the recent sales before you read it as a bargain.

Guide formats we understand

"$950,000", "950k", "$900k – $950k", "1.2m", "1.2 – 1.3m", "Offers over $850,000". With a range, we use its midpoint.

4 · Recent sales

Which sales we show

Sales of the same type (houses with houses, apartments with apartments) from the last 3 months, in this order:

  1. Same building for apartments, or same address for houses.
  2. Same street.
  3. Elsewhere in the suburb, closest in size first, within −25% to +33% of this property's area.
  4. If that gives fewer than three, other suburbs in the postcode, then any size in the postcode.

The summary price per m² is the median of the similar-sized sales, multiplied by this property's area. It's a quick cross-check on the model: if the two are far apart, the property or its recent neighbours may be unusual.

5 · Accuracy

Tested on sales it never saw

To test it fairly, the model was trained only on sales before 1 August 2026, then asked to price the 16,308 sales from August to November 2026. The test sales were never used to tune it.

GroupSalesMedian errorWithin 10%Within 20%
All sales16,30810.1%50%75%
Houses9,98410.5%48%73%
Apartments6,3249.4%52%77%
Sold before11,6489.1%54%79%
No earlier sale on record4,66013.3%40%65%

So a typical estimate is about 10.1% from the eventual price; half land within 10% and three in four within 20%. Each week we also score the model on the newest sales before adding them to training: 10.5% median error for the week of 9 Nov 2026 and 10.9% for 16 Nov 2026.

6 · Limits and data

What it can't see

Data

Property sales: NSW Valuer General bulk property sales information, 1990 to the latest weekly file (CC BY-NC-ND 4.0). Addresses and locations: G-NAF © Geoscape Australia (CC BY 4.0). The model is retrained each week as new sales are published.

This is an automated estimate, not a formal valuation. Do your own research and get professional advice before buying.

Ready to check a property?

Check a property →