ROC Curve
- ROC = Receiver Operator Characteristic
- ROC curve is used to compare one classifier with multiple parameters
- Usually used to find the threshold point of the output
- X-axis -> True Positive Rate or Sensitivity
- Y-axis -> False Positive Rate or (1 - Specificity)
- If you need to compare multiple models, then AUC Score
- The point on the top is best for classifying positive instances but might not be good for negative one
- The point on the top left is the optimal one (TPR - FPR Tradeoff)