The map is the product
ValueAtlas is not a dashboard with a map attached. The map is the primary canvas, time is the primary control, and AI is the primary guide. Every insight is geocoded, timestamped and connected to the properties around it.
The platform
An operating system for the physical world, beginning with real estate.
ValueAtlas is a map-first platform for real estate value. It answers four linked questions about any place — what happened, where, when, and what likely happens next — and it shows its work with confidence bands rather than a single number.
Four product principles
Motion is the interface
Weather forecasting taught the world to read patterns by watching them move. Real estate value has the same structure — waves, fronts, reversals and diffusion — and ValueAtlas renders it the same way, animated at 60 frames per second.
Every forecast is remembered
Each prediction is written to an immutable registry with its model version, inputs, horizon and confidence band. As reality arrives, the gap between forecast and outcome becomes a proprietary calibration dataset.
Confidence over certainty
Forecasts are always shown as ranges. Recorded history is visually separated from modelled estimate, and thin source data lowers displayed confidence rather than hiding it.
What the platform does
Time scrubber
Drag a single control from 2016 to 2036 and watch the value surface of a city redraw. History is fitted from recorded deeds and MLS records; anything past the present is model forecast at P50 with a visible band.
Property and neighborhood cards
Every parcel and every neighborhood has a permanent page: current estimate, forecast range, the signals driving it, and the comparables the model leaned on.
Event engine
Developments are tracked through five states — rumored, proposed, approved, built, operational. Markets reprice long before completion, so the model reprices with them.
Hazard and carrying cost layers
Wildfire exposure, flood elevation, insurance availability and premium drift are priced directly into forecasts, because carrying cost increasingly determines what a property is worth.
Forecast registry
An append-only log of every prediction ValueAtlas has published, queryable by market, horizon and regime, with calibration reported openly.
Enterprise portfolio monitoring
Lenders, insurers and portfolio managers can watch thousands of positions at once, with alerts when a submarket's forecast or confidence shifts materially.
Who uses ValueAtlas
- Homeowners and buyers
- Understand a neighborhood before committing to it — what has happened, what is happening, and the range of what happens next.
- Investors and developers
- Underwrite appreciation and rental yield at parcel level, with named downside scenarios instead of a single optimistic number.
- Lenders and insurers
- Monitor concentration and hazard exposure across a book of properties, and see forecast confidence degrade before losses arrive.
Where it is live today
- New York — Manhattanlive · 98%
- New York — Brooklynlive · 94%
- San Francisco Baybeta · 78%
- Greater Los Angelesbeta · 71%
- Puerto Vallarta — Marina Vallartabeta · 62%
Read how the model works or request early access.