Skip to main content

Table 8 Results for Random Forest

From: Detecting web attacks using random undersampling and ensemble learners

Sampling

AUC

SD AUC

AUPRC

SD AUPRC

None

0.64003

0.01826

0.37562

0.05405

999:1

0.65047

0.0163

0.35197

0.0348

99:1

0.72736

0.02866

0.32367

0.03301

95:5

0.79801

0.02154

0.26788

0.0775

9:1

0.81982

0.02427

0.26089

0.06329

3:1

0.92439

0.02171

0.25407

0.07858

65:35

0.9413

0.0065

0.2426

0.10392

1:1

0.94345

0.00653

0.1624

0.08754

  1. Sampling column reports negative to positive class ratio after applying random undersampling, or “None” for case when no undersampling is applied
  2. AUC stands for Area Under the Receiver Operating Characteristic Curve, SD stands for standard deviation reported for every metric, AUPRC stands for Area under the Precision-Recall Curve