Table 6.

A comparison between CFA Huang et al. (2003) and FRaC using average probability (Eq. 3) to measure the extent to which discretization affects anomaly detection

Feature predictor	CFA	AP FRaC	p-value
Decision/regression tree	10	32	0.000133
Linear Kernel SVM	9	33	0.000697
RBF Kernel SVM	13	28	0.00416
Tree, linear and RBF SVM combined	11	29	0.000925

Columns have the same meaning as in Table 4. (Rows for naïve Bayes and RIPPER are not shown because these approaches are the same when discretization is required)