Story
Fortescue Runs Applied Machine Learning with Confluent
Fortescue, a materials organization in Australia, uses Connect from Confluent to support applied machine learning for data scientists and ML engineers.
Value results
| Category | Value result |
|---|---|
| Capability | Feature pipelines can be reviewed without waiting on a personal export |
| Capability | Named workflow replaces ad hoc routing for feature pipelines |
| Capability | Applied machine learning stays visible to adjacent teams through Connect |
Story
Fortescue grew feature pipelines faster than the local tools around it. From Australia, materials teams still had to serve customers and internal partners who expected a straight answer. Data scientists and ML engineers were the ones stitching the picture together by hand.
Rolling out Connect put applied machine learning on Confluent. Confluent is the data streaming platform built around Apache Kafka, used to move events between applications in real time. Fortescue keeps the product in the path where work already happens, so data scientists and ML engineers do not context-switch into a graveyard system used only for audits.
The visible result is steadier applied machine learning. Feature pipelines is easier to inspect, and adjacent groups can join data scientists and ML engineers without a guided tour of someone's desktop.