AI engineering glossary · Evaluation metrics
What is ROC curve?
ROC curve (also called receiver operating characteristic curve): A plot of the true positive rate against the false positive rate as the decision threshold of a scoring classifier sweeps from strict to lenient. Each point is one threshold. A curve hugging the top-left corner means a strong classifier, and the diagonal means random guessing.
ROC curve: an example
A credit-risk model that scores applicants can be run at 50 thresholds; plotting each threshold's (FPR, TPR) pair gives its ROC curve.
Related terms
More Evaluation metrics terms
- Root mean squared error
- Root mean squared logarithmic error
- ROUGE
- ROUGE-L
- Slice-based evaluation
- Spearman's rank correlation
- Specificity
- Symmetric mean absolute percentage error
Where you learn it
ROC curve is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.