Evaluation
Precision
Precision is the fraction of predicted positives that are truly positive.
How it works
It answers how often a positive alert is correct. Precision matters when false positives are costly.
A concrete example
Illustrative: 72 true positives and 18 false positives give precision 72/90 = 0.80.
Do not confuse it with Recall
precision conditions on predictions; recall conditions on actual positives.