TABLE III. Evaluation Results of ML Methods With an 80–20 Train–Test Split Technique on the Normalized Dataset, Along With Brute-Force Feature Selection.

Classifiers	F1	Precision	Recall	Accuracy	AUC
RF	93	95	94	94.16	0.93
Bernoulli NB	89	86	93	92.5	0.89
SVM	94	95	95	95	0.95