30%+
“saved an estimated 30%+ in total time, plus months of custom development work in engineering hours”
As published on labelbox.com. Captured by usedby on Oct 7, 2026.
What happened
Cape Analytics runs an iterative active-learning cycle in its model training pipeline, using Labelbox to surface low-confidence geospatial predictions and route them to data scientists and contributors for correction. This targets the model's blind spots, such as confusing natural features with yard debris.
Summary written by usedby from the source page, in English. The figures are those of Labelbox and Cape Analytics, not ours.
The combination of queue management and active-learning cycles saved an estimated 30%+ in total time, plus months of custom development work in engineering hours.
There are many data tools out there but the Labelbox backend is the real differentiator. With dynamic queueing, our team of experts are never out of work, which was a major upgrade compared to our old internal tools — both from a productivity and speed-to-production point of view.
What the story claims, and what we checked
We compared the story with its live page on Oct 7, 2026.
- The figure: 30%+CheckedPrinted word for word on the page, near the name of Cape Analytics.
- The passage quoted aboveCheckedCopied word for word from the page, near the name of Cape Analytics.
- Cape Analytics uses LabelboxCheckedConfirmed line. Latest check across sources: Oct 7, 2026.
- The result itselfNot checkedWe quote it; we did not measure it.




