Decision tree learning: Difference between revisions

Revision as of 20:44, 21 November 2022

Revision as of 11:12, 5 December 2022

Line 107:

=== Estimate of Positive Correctness ===

WhenA correctlysimple and effective metric can be used to identify the degree to identifyingwhich true positives outweighs identifyingoutweigh true negatives (see [[Confusion matrix]]). likeThis when using decision trees for cancer researchmetric, a"Estimate simpleof yetPositive effectiveCorrectness" metricis candefined be used.below:

This metric, "Estimate of Positive Correctness" is defined below:

<math> E_P = TP - FP </math>