Extraction cases, by source name.
One case file per source — the largest system we run against each of them. Each card opens the full file: what the client needed, what the source put in the way, how the pipeline is built and what the numbers are today.
Idealista
Three countries, 12M properties, one model
A fund buying across southern Europe cannot compare a Madrid listing to a Lisbon one until both are the same shape.
- property records to date
- 12B
- measured coverage
- 98.4%
Realtor.com
The market, and the 1.9M people selling it
For a platform selling to agents, the interesting entity is not the property — it is the agent. Which listings are theirs, how fast they move, which brokerage they sit under this month, and which of them just lost a listing to a competitor down the road.
- records to date
- 17B
- measured coverage
- 98.5%
Airbnb
7.4M listings, 210M calendar-nights a day
Short-let revenue management lives or dies on two things: how much comparable supply exists in a neighbourhood, and what that supply actually costs a guest once cleaning and fees are added.
- calendar-nights since 2023
- 230B
- measured coverage
- 97.2%
Expedia
46M itineraries priced a day, decomposed
A package price is deliberately not the sum of its parts, and that difference is the entire product for anybody selling travel pricing intelligence.
- itineraries priced since 2024
- 30B
- measured coverage
- 98.1%
Skyscanner
94k routes, 210M fare quotes a day
Airfares change several times a day, exist for every combination of date, carrier and fare class, and are worthless the moment they are stale.
- fare quotes since 2024
- 150B
- route coverage
- 97.8%
eBay
340M listings watched, sold prices captured
For anything second-hand, the asking price is an opinion and the sold price is a fact. The client needed the facts — at category scale, across five markets, with enough seller and condition detail to explain why two identical items sold eleven days and forty per cent apart.
- sold records to date
- 2.6B
- measured coverage
- 98.0%
Mercado Libre
84M listings, eight markets, eight currencies
Eight countries, eight currencies, and in two of them a rate that moves enough within a month to make a monthly average meaningless.
- offer records since 2022
- 105B
- measured coverage
- 97.9%
Allegro
64M offers, competition at the offer level
On a marketplace where the same product is sold by forty accounts, the product price is meaningless. What decides whether a sale happens is the specific offer — its delivery terms, its badge status, its position — and that is what the client's pricing team had never been able to see.
- offer records since 2022
- 96B
- measured coverage
- 98.8%
Target
1 950 stores, promotions caught the day they turn
Promotional effectiveness is measured against what actually ran, in which stores, on which days. A feed that reads promotions three days late does not measure effectiveness — it measures something adjacent to it, with an error nobody can quantify.
- SKU-store rows a year
- 9.9B
- measured coverage
- 98.9%
Clients stay anonymous — every engagement is under NDA, and what is published here is what each of them agreed to publish. Under NDA we walk through the architecture, the failure modes and the cost model of any of these against the source you actually care about. Case files for the other three disciplines are in preparation.
Start here
Have a source of your own? Two lines are enough.
Send the source, the fields you need and roughly how often. You get a straight answer within 24 hours: whether it can be done, what makes it hard, what coverage is achievable and roughly what it costs to build and to run. Whatever the size.
Direct
NDA before technical detail, as always. If it isn't our kind of work, we say so in the first reply.