Public Sector & Real Estate · Geospatial data science · 14 weeks
638,000 properties, ranked down to the 100 they could actually act on.
Every parcel in the state scored on the same 45 measures, so that “which property should we buy next?” finally had an answer that did not depend on who walked in the door.
6,382 : 1
Reduction from every property in the state to a shortlist a board could read in one sitting
This authority exists to buy neglected property and get it back into use. The data to find those properties existed — ownership records, environmental registries, census tracts, parcel maps — but in separate systems with nothing linking them. In practice the next purchase was decided by whoever brought it up.
We put every property in the state into one record, then scored all of them the same way: how close each sits to the things that make a place liveable, how long it has been neglected, how tangled the ownership is, and how likely the authority is to be able to buy it at all.
The useful finding was how rare a good target is. Of the 63,706 properties in the top tier, only 205 were publicly owned — the ones they could move on without a negotiation. Those clustered in a handful of towns, which turned a statewide mandate into a short list of places to actually drive to.
A state-chartered land bank authority, US Northeast
What it came down to
- One record per property, joined from five sources that had never been linked
- Only 205 of 638,184 combined high impact with a realistic chance of purchase
- Interactive maps so board members could check the reasoning without an analyst
- Parcels scored
638,184
Parcels scored
- Ownership records reconciled
249,034
Ownership records reconciled
- Measures per parcel
45
Measures per parcel
What this doesn’t tell you
Census and environmental inputs lag real conditions, and ownership records covered 39% of parcels — so the score ranks confidence as much as opportunity.
Clients are described by sector, scale and region only. No names, products or identifiers appear here.
Next step
Have a version of this problem?
Tell us what you are trying to build. You will get an honest read on whether it is worth building at all.
What happens next
- You pick the workflow. We ask what already exists, who touches it, and where it stalls.
- We reply within one business day with a rough shape and a rough timeline — usually smaller than people expect.
- If it makes sense, the next step is a working system in two to six weeks, tested by your own staff.
- You keep your existing tools. Private deployment is available where data cannot leave.
- And if it is not worth building, we say so instead of selling you one.