35,000 to 50,000 procurement lines a month classified to UNSPSC, from zero, for Strukton
Strukton is a major Dutch infrastructure contractor. Pearstop built this system together with their procurement department. It classified every line of spend into UNSPSC, automatically, every month.
Why can’t you find procurement savings without granular spend data?
Strukton had identified a real cost-saving opportunity in procurement. To act on it, they needed higher granularity in their spend data. Their spend was already well organized. What they didn’t have was UNSPSC classification. This project started from zero classification history.
How does an AI classification system avoid guessing on your data?
Pearstop and Strukton’s procurement team built a system with three layers, avoiding the most common mistake in AI projects: reinventing the wheel without giving the model enough context to work from.
2 · ML pipeline learned from context
3 · Human-in-the-loop for the rest
Why do all four UNSPSC levels matter, not just the top one?
Every month, a new batch of spend came in. Pearstop processed all of it. Each line got four levels of UNSPSC classification: segment, family, class, and commodity.
A segment is the broadest category. A commodity is the most specific. Classifying to all four levels, not just the top one, is what makes the data usable for real decisions — benchmarking one specific product across suppliers, not just a broad category average. Read more about how UNSPSC’s four levels work.
“Built and proven with a major Dutch infrastructure contractor, starting from zero classification history.”
More accurate every month, not just more used
Strukton's buyers reviewed what the AI classified, flagged what was right and what wasn't, and every correction fed back into the system. Pearstop and Strukton's team met weekly to go over what was working and what wasn't.
From zero classification to full granularity
Before this project, Strukton had no UNSPSC classification at all. By the end of the engagement, 35,000 to 50,000 lines of spend were classified automatically every month, to all four UNSPSC levels. That is the granularity the original cost-saving opportunity needed to actually be acted on.
Want a case study built around your data?
We can show you what the same approach would look like for your procurement or asset data.
