Measuring Mistakes

Precision and recall

An interactive lesson with 7 steps, about 6 minutes: you predict, drag and solve, with instant feedback on every answer. It runs in your browser and needs JavaScript.

What you’ll learn

• Accuracy misleads when one class is rare.
• Recall = TP/(TP + FN); precision = TP/(TP + FP).
• Moving a threshold trades recall against precision.

Steps

1. A lazy detector
2. Four kinds of outcome
3. Moving the threshold
4. Catch 90%
5. Tracing the ROC curve
6. Precision from counts
7. One number for both