Table 4. Optimal parameters selected for each classifier.

Models	Optimal tuning parameters
LR	none
KNN	k = 3
C5.0 DT	trials = 20
	model = tree
	winnow = false
ANN	decay = 0
	size = 7
RF	mtry = 46.88889
XGBoost	nrounds = 200
	lambda = 0
	alpha = 0
	eta = 0.3
svmLinear	C = 2.154
svmRadial	C = 1000
	sigma = 100