When should you use PR-AUC instead of ROC-AUC?
mediumAnswer
- Use PR-AUC when the positive class is rare (heavy imbalance).
- ROC-AUC can look optimistic on imbalanced data because the true-negative rate dominates the false-positive rate.
- PR-AUC only involves the positive class (precision and recall), so it reflects real performance on the minority class.
Check yourself — multiple choice
- ROC-AUC is always the best metric
- PR-AUC is preferred for highly imbalanced classes
- Both are identical mathematically
- PR-AUC ignores true positives
On rare-positive problems, ROC-AUC is misleading; PR-AUC focuses on the minority class.
#metrics#imbalance
Practise Supervised Learning
215 interview questions in this topic.
Related questions
- Why is accuracy a bad primary metric for many real-world problems?
- What is Cohen's kappa and why is it useful?
- What is the Matthews Correlation Coefficient (MCC) and when should you use it?
- What is balanced accuracy?
- What is the geometric mean (G-mean) in classification metrics?
- What are the main pitfalls of relying on ROC-AUC?