Methodology
How we estimate home value
The data, the model, and the limits. We'd rather be honest about what our estimate can and can't tell you than pretend it's infallible.
In plain English
When you enter an address, our system pulls public records for that property (recorded sale prices, parcel details, tax assessments), identifies comparable sales in the same area, and applies an AI model calibrated on hundreds of thousands of historical transactions to produce a value estimate and a confidence range.
It is not a substitute for a licensed appraisal or a comparative market analysis. It is a fast, reasonable starting point — the kind of number you'd want before making a phone call, not before signing a contract.
What data we use
Public records
- • Recorded deed transfers
- • Parcel & tax assessor data
- • Historical sale prices
- • Property characteristics (beds/baths/sqft/lot size)
Refreshed as counties publish updates
Market signals
- • Neighborhood sale trends (90-day rolling)
- • Days-on-market
- • List-to-sale ratios
- • Market-level mortgage-rate context
Weekly refresh
Property-specific inputs
- • User-supplied condition & updates
- • Photographs (when provided)
- • Reported renovations & permits
Per-request; apply only to that estimate
Specific data providers are listed in our vendor-disclosure document (available on request).
How the model works
The estimate is produced by a calibrated ensemble: a gradient-boosted model trained on historical sales informs the central estimate, and a comparable-sales adjustment refines it using the five to twenty most-similar recent sales within the same market.
The confidence range you see is not a guess — it's a quantile estimate. The upper and lower bounds are the points at which 80% of historical predictions on similar properties fell inside the band. Properties with thin comp coverage or recent major renovations produce wider bands; properties in dense, active markets produce narrower ones.
We re-calibrate against observed outcomes on a rolling 90-day window. When a property sells, we measure our pre-sale estimate against the recorded sale price and feed that error back into market-specific adjustment factors.
Accuracy & limits
Public AVMs benchmark their accuracy with Median Absolute Error — the middle of the error distribution on recent sales. We're in the process of publishing our own per-market MAE on a rolling basis. In the meantime, here's what we know about where our estimate is most and least reliable.
Where the estimate is strongest
- Single-family homes in active suburban markets
- Properties with at least five comps within 0.5 miles in the last 12 months
- Homes between 1,200 and 4,500 sq ft built after 1950
- Standard-grade construction (not custom or luxury tier)
Where error is higher
- New construction with no comparable sales history
- Rural properties (sparse comps; acreage drives value)
- Unique or custom architecture
- Luxury tier ($3M+) where each sale is effectively bespoke
- Properties recently renovated in ways not yet in public records
- Markets with low transaction volume in the past 12 months
What's still being validated
- Per-market MAE tables (top-20 MSAs × property type) — publishing Q3 2026
- Quarterly accuracy dashboard — publishing Q3 2026
- Independent third-party validation benchmark — planned
When you should get a CMA instead
An instant estimate is a research tool. It's not the right tool for these decisions:
- Setting a list price. A licensed agent's CMA can see the specific home's condition, recent upgrades, and micro-market context an AVM can't.
- Qualifying for a refinance or cash-out. Lenders require an appraisal. Don't rely on the AVM number for underwriting decisions.
- Negotiating a contract. Use the AVM to sanity-check; don't rely on it as the anchor number.
- Tax assessment disputes. Jurisdictions typically want evidence from appraisal reports or comparable-sale affidavits, not AVM screenshots.
Report a bad estimate
If you know an estimate is materially wrong — say your house just appraised for $100,000 more or less than our number — tell us. Corrections feed our calibration pipeline, and we flag known-bad estimates in the UI.
Frequently asked
›Where does the estimate data come from?
Estimates combine public records (deed transfers, recorded sales, parcel + tax assessor data), regional market trends, and — where available — user-supplied details about the specific property. The platform does not have direct MLS access, so active-listing data used to inform market context is derived from public aggregators, not the underlying MLS.
›How accurate is a PropertyTools AI home value estimate?
Accuracy varies meaningfully by market, property type, and data freshness. Typical-case error is competitive with public AVMs (Zestimate and Redfin Estimate both publish on-market MAE in the 1.8–2.0% range), but edge cases — new construction, rural markets, unique architecture, recent renovation — can produce larger errors. Market-specific error numbers are in development and will publish here once a rolling-90-day sample is statistically stable.
›How often is the estimate updated?
Underlying market data and comparable sales refresh on a rolling cadence. Individual address estimates recalculate on each request, so the value you see reflects the most recent data at the moment of the query. Update cadence for specific data feeds is documented below.
›When should I use a real CMA instead?
An AVM-based estimate is useful for quick benchmarking. If you're pricing to sell, qualifying for a refi, or making a contract decision, use a full comparative market analysis (CMA) prepared by a licensed agent who can inspect the property, weight comps by hand, and account for recent improvements. PropertyTools AI offers a CMA-report generator separately, and real licensed agents via LeadSmart AI.
›What if my estimate is wrong?
Report it. We track flagged estimates, feed corrections back into our calibration pipeline, and surface known-bad estimates with a warning flag. See the “Report a bad estimate” section below.
›Do you train AI models on user-submitted data?
User-submitted property details are used to refine estimates for that specific address. Aggregated, de-identified patterns inform model calibration across markets. Personally identifying information and address-level inputs are not used for generalized model training.