📊 ROC vs. PR Curve: Key Differences




ROC Curve
- 📈 Plots: True Positive Rate vs. False Positive Rate
- 🎯 Best for: Balanced datasets
- 📉 AUC baseline: 0.5
- 🧠 Measures: Overall model performance
PR Curve
- 📈 Plots: Precision vs. Recall
- 🎯 Best for: Imbalanced datasets
- 📉 AUC baseline: Depends on positive class frequency
- 🧠 Measures: Positive class performance
✅ Tip:
Use ROC for general evaluation, PR when positives are rare.
Use ROC for general evaluation, PR when positives are rare.