A metric that measures the fraction of relevant items that a system successfully retrieved or identified.
Friendly Description: Recall measures how good a system is at finding all the things it should find. Imagine you're searching your inbox for every email about a project. If there are 10 such emails and your search turns up 8, your recall is 80%. High recall means few misses, which matters a lot in things like medical screening or fraud detection.
Example: A system that flags potentially fraudulent transactions might catch 95 out of 100 real frauds. That's 95% recall. The remaining 5% slipped through, which is why recall is closely watched in any application where missing a real case is costly.