How First Access Signals works
First Access Signals tells you when to act on a home, not just what a home is worth. The Service combines three things into one app:
1.
A Signal, a 0 to 100 score for any GTA home that estimates the chance the home would sell within 30 days at or near its asking price, and the verdict on whether now is a good moment to list.
2.
An estimate of the home's likely sale price, shown as a range, so you can see where a sale is most likely to land.
3.
A Buy Signal for neighbourhoods, which ranks active listings by timing, value, and lifestyle fit so a buyer can focus on the homes most likely to be a good move right now.
First Access Signals is licensed under the Toronto Regional Real Estate Board (TRREB) Virtual Office Website (VOW) Datafeed Agreement and is operated by Keith Godding under THE AGENCY brokerage.
What the Signal score means
The Signal is a forecast, not a guarantee. Read it the way you read a weather forecast. A high score means a strong chance the home sells at or near its asking price within 30 days; a low score means a weak chance. The percentages are honest: when the Signal says about 6 in 10, about 6 in 10 homes actually sell at the asking price.
The 0 to 100 score falls into one of three bands. The rates below are measured on about 119,000 listings the model never saw, counting every home whose first 30 days have passed, including the ones that did not sell. Success means selling within 30 days at or near the asking price (within about 5 percent of the asking price).
Green (60 to 100)
About 34 percent of these homes sell at or near the asking price within 30 days. A strong moment to list.
Amber (50 to 59)
About 23 percent do. Pricing decides the outcome.
Red (0 to 49)
About 13 percent do. The other 87 percent need a lower price or more time. For a buyer, that is room to negotiate.
A green Signal at about 34 percent is not an error rate. It is how often homes in that band sell at the asking price. Across every band, the rate we forecast stays within a few percentage points of what actually happens, the reliability standard described below.
Updated 8 September 2026. Until this date, a home taken off the market before its 30 days were up was left out of the count altogether. That made the chance of selling shown on each listing read kinder than the market was, because it counted the homes that sold and the ones that sat, and quietly dropped the ones that gave up. Those attempts now count as what they were: a home that did not sell. The chance shown on a listing is lower as a result, and it is the real one.
One exception keeps the count fair. A listing that comes off the market and goes straight back up at the same asking price is the same attempt carrying on, not a failed one, so it is counted once rather than twice.
What the market read means
Next to a home's Signal, each listing shows a market read: a buyer's, balanced, or seller's market. The two answer different questions. The Signal is about this home and how much demand it is drawing. The market read is about the neighbourhood around it and which side conditions favour right now.
The market read is graded from the recent balance of supply and demand for that community and property type: how close homes are selling to their asking prices, how long the homes now for sale would take to sell at today's pace, and where interest rates are. We read the home's own community first, then fall back to its postal area and the wider GTA when a community has too few recent sales to stand on its own.
The two reads can point different ways, and that is by design. A home in strong demand can sit in a buyer's-market neighbourhood, and a quiet home can sit in a seller's one. Read together, the Signal tells you how this home is doing and the market read tells you which way the neighbourhood is leaning.
Data sources
First Access Signals uses the TRREB VOW data feed, which provides a 24-month rolling history of every listing in the GTA, including final sale prices on closed deals. The Service combines the listing data with broader economic and neighbourhood data that tends to move before home prices do:
•
Bank of Canada policy rate.
•
Statistics Canada housing-starts and building-permits data at the Census Metropolitan Area level.
•
Canadian Real Estate Association (CREA) Home Price Index for the GTA.
•
Toronto building-permits and crime data at the neighbourhood level.
•
TTC and GO Transit schedule data for commute distance calculations.
•
Statistics Canada 2021 Census demographics at the forward sortation area (FSA) level.
•
Fraser Institute school ratings.
First Access Signals does not buy data from credit bureaus. The Service does not use any data it is not authorized to use under the VOW Datafeed Agreement.
How we measure accuracy
This is the part that makes First Access Signals different from other Canadian home-value tools.
For the Signal (a probability)
First Access Signals measures accuracy with the Brier score and the Brier Skill Score (BSS).
In plain English:
•
The Brier score measures how far off the model's percentage predictions are on average. Lower is better. A perfect score is 0.0; a score of 0.25 is the score of a model that always says "50 percent."
•
The Brier Skill Score (BSS) measures how much better the model's forecasts are than guessing the market average every time. Zero means no better than guessing the average; 100 means perfect. Measured on listings from May to July 2026, the Sell Signal score sits at about 6 percent. We restate this number each time the model is rebuilt.
•
First Access Signals also publishes reliability, which checks that when the model says "60 to 70 percent chance of selling," the actual rate falls in that band. The target: never off by more than 10 percentage points, in any band.
Current published values (30-day Signal):
•
Brier score: 0.131, measured on listings from May to July 2026. Anything at or under 0.18 counts as healthy.
•
Brier Skill Score and reliability: refreshed each time the model is rebuilt.
For the predicted sale price (a dollar value)
First Access Signals measures accuracy with the median absolute percentage gap: the middle of how far our predicted sale price sits from the real selling price, across sold homes the model was not built on. Lower is better. Half of our predictions land closer than the median gap, and half land further.
The current figures are drawn live from our prediction record on the
receipts page, so there is one number rather than a copy of it here that can drift.
We record every prediction before the home sells, so these figures are measured against what actually happened, not fitted after the fact.
Where the model performs well, and where it performs less well
First Access Signals publishes where the model is most accurate and where it is least, by neighbourhood. Being honest about the weak spots is part of the product. The lists refresh each time the model is rebuilt.
PENDING NEXT RETRAIN
The ten best and ten worst postal areas will publish here after the next model rebuild. If your home is in an area where the model is less accurate, the app marks the result, and the estimate is best treated as a starting point for a conversation with Keith rather than a precise number.
How the model remains honest over time
A real estate model that was built on 2024 data and never re-checked would drift further from reality every month. First Access Signals keeps the model honest five ways:
1.
Early warning data. First Access Signals uses Bank of Canada and Statistics Canada releases to catch market shifts before they show up in sales.
2.
Prices adjusted for the market tide. Where it improves accuracy, sale prices are adjusted by the CREA Home Price Index so the model learns what is specific to the home, not the market tide.
3.
Recent sales count for more. Recent sales weigh more than older ones when the model learns.
4.
A tripwire on repeated misses. If the model's misses start leaning the same way week after week, it is flagged and rebuilt.
5.
Regular rebuilds. The model is rebuilt on the latest 24 months of sales on a reviewed schedule. Between rebuilds, predictions for active listings refresh several times a day against the newest model and fresh neighbourhood and building data, so the numbers track the current market.
If the published accuracy numbers fall below the healthy marks in two rebuilds in a row, First Access Signals publishes a notice on this page describing what changed and what is being done.
Common questions
How accurate are the predictions?
We grade the Likely Sale Price we showed while a home was listed against the price it actually sold for. The median gap is 2.2% and we published the result on every listing.
What makes First Access Signals different?
Most sites stop at what a home is worth. First Access Signals reads the whole market: a 0 to 100 timing read on every GTA home, for buyers and sellers, with the predicted sale price layered on top and the result published on every closed listing.
What does it cost?
Nothing. The signals, the accuracy receipts, and your home's own timing read are all free.
Why do some things need a free account?
The MLS® rules that give us live listing data draw a line between active listings and sold records. Anyone may browse what is for sale. Sold prices, and your own home's value, may only be shown to a signed-in person with a genuine interest in buying, selling, or leasing. Your free account is that assurance.
Who is Keith Godding?
Keith Godding is a REALTOR® at THE AGENCY. Licensed since 2017, he has closed millions of dollars of business and built First Access Signals to give people the tools to make the best decisions for themselves and their families.
VOW compliance and the bona-fide-consumer commitment
To use the parts of First Access Signals that show specific listing details, you must be a registered user, which means you have signed in with Apple, Google, or email and acknowledged the following statement, required verbatim by the TRREB VOW Datafeed Agreement §6.3(k):
The information provided herein must only be used by consumers that have a bona fide interest in the purchase, sale, or lease of real estate and may not be used for any commercial purpose or any other purpose.
If you are not a bona-fide consumer (for example, you are a researcher building a competing data product), please do not register.
The brokerage of record is THE AGENCY, and the designated REALTOR® for First Access Signals is Keith Godding.
Plain-English glossary
Brier score
How far off the model's percentage predictions are on average. Lower is better.
Brier Skill Score (BSS)
The percentage of prediction noise the model removes compared with always guessing the market average. Currently about 6 percent, restated each time the model is rebuilt.
Reliability max-deviation
When we say 60 to 70 percent chance of selling, the actual rate falls within 10 percentage points of that band.
Median absolute percentage gap
The middle of how far our predicted sale price sits from the actual sale price. Lower is better.
Walk-forward backtest
Predicting each calendar quarter using only data from before that quarter. If our error grows quarter over quarter, we know the model is going stale and we retrain.
Drift detector
If the model's accuracy is drifting more than five percent per quarter, we retrain.
Bona-fide consumer
A real person looking to buy, sell, or lease a home, not a researcher or a competitor scraping data.
VOW (Virtual Office Website)
TRREB's data-feed program that lets registered REALTORS® and their clients see listing details.
MLS attribution
Every listing card on our app shows the listing brokerage's name and the MLS source.
Market read
Whether a home's neighbourhood is a buyer's, balanced, or seller's market, graded from how close homes sell to asking and how much inventory is on the market. Separate from the home's own Signal.
FSA
Forward sortation area. The first three characters of a Canadian postal code (for example, M5V).
Contact
This page is the official methodology disclosure for First Access Signals. It is updated quarterly or when the model changes materially.