AI Glossary Term
What does “Recall” mean?
Definition
The proportion of actual positives that a model correctly identifies.
How Recall works
Example
A screening model reviews 100 scans that truly show disease and flags 85 of them. Its recall is 85 percent; the 15 missed cases are the cost, which can be serious in medicine.
Why it matters
High recall means few real cases slip through. It matters most when misses are dangerous, such as in disease screening or fraud detection.
Common questions
Recall vs precision?
Recall is about finding all real cases. Precision is about how many of the flagged items are correct.
Another name for recall?
Sensitivity or true positive rate.
Can I raise recall easily?
Yes, by flagging more, but that usually lowers precision. Teams choose a balance for their purpose.