ROC curve – ML

The ROC curve(relative operating characteristic curve), is a comparison of two operating characteristics (TPR and FPR) as the criterion changes (sensitivity as a function of fall-out).

The TPR(true positive rate) is also known as sensitivity, recall or probability of detection, it can be calculated as 1-miss rate(FNR).

The FPR(false positive rate) A.K.A the fall-out or probability of false alarm, it can be calculated as 1-sensitivity(TNR).

 

A receiver operating characteristic curve, is a graphical plot that illustrates the TPR) against the (FPR) at various threshold settings of a binary classifier system, and finding the max TPR against the min FPR value.

 

  • False positive rate (FPR)(α) = type I error = 1 − specificity
    = FP / (FP + TN) = 180 / (180 + 1820) = 9%
  • False negative rate (FNR)(β) = type II error = 1 − sensitivity
    = FN / (TP + FN) = 10 / (20 + 10) = 33%
  • True positive rate (TPR)Recall, Sensitivity, probability of detection
    =Σ True positive/Σ Condition positive
  • Accuracy (ACC)
    = Σ True positive + Σ True negative/Σ Total population
  • Precision
    = Σ True positive/Σ Predicted condition positive