30k
lines classified per decision
Case Study
Accurate margin estimates on every container purchase, automatically
For every purchasing decision, FARO needed to categorise around 30,000 product lines per five containers to estimate margin, sale price, and stock time. Manual categorisation made this slow and inconsistent. Pearstop automated the classification using their own category system and linked it directly to their sales database.
Retail · South Africa
The challenge
For each container purchase, FARO needed a reliable cost picture before committing capital. That meant classifying thousands of product lines, linking them to sales outcomes, and keeping the process fast enough to support the buying decision itself.
Without automation, the work was repetitive, slow, and hard to scale. With Pearstop, the team got a structured process that could support margin estimation before the purchase was made.
1 wk
classification time
Sales
database linked
What Pearstop delivered
Automatic classification
Pearstop classified 95% of the items in under a week, using the company's own category logic.
Sales-linked margin view
The dataset was linked to sales information so buyers could see margin before the purchase happened.
Decision speed
The team stopped spending days on manual categorisation and got a clean basis for the buying decision itself.
We had thousands of product lines that needed to be categorised before we could even begin to understand our costs. Pearstop classified them in under a week. That would have taken our team six months and still would not have been this accurate.
What changed for FARO?
The team moved from manual categorisation to an automated flow that could keep up with buying decisions. That made margin visible earlier, reduced the operational drag on the procurement team, and gave the business a more reliable basis for planning and analysis.
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.