Glossary · Machine Learning
What is Precision and Recall?
Two classification metrics: precision is how many flagged items were correct; recall is how many actual positives were caught.
In more detail
They trade off against each other through the decision threshold. Choose based on which mistake is costlier; F1 combines both.
Example
A spam filter needs high precision; a cancer screen needs high recall.
Learn it properlyModel Evaluation Metrics: Confusion Matrix, Precision, Recall, F1 and Cross-Validation12 min lesson · Machine Learning