Professional Documents
Culture Documents
Evaluation Method Holdout
Evaluation Method Holdout
P’ is the number of tuples that were labeled as positive (TP +FP) and N’ is the number of
tuples that were labeled as negative (TN +FN). The total number of tuples is TP +TN +FP
+TN, or P +N, or P’ + N’. Note that although the confusion matrix shown is for a binary
classification problem, confusion matrices can be easily drawn for multiple classes in a
similar manner.
C TP FN P fraud, or HIV-positive
Significant majority of the
¬C FP TN N
P’ N’ All negative class and minority of
the positive class
Classifier Accuracy, or Sensitivity: True Positive
Precision = TP/TP+FP
90/300 = 30.00 (sensitivity)
= 90/230 = 39.13%
9560/9770 = 98.56 (specificity)
Recall = TP/TP+FN 9560/10000 = 96.40 (accuracy)
= 90/300 = 30.00%
— Hold aside one group for testing and use the rest to build model
— Repeat
iteration
Test