Table 2.

Performance analysis of test data using traditional machine learning technique with feature reduction (Technique 2).

ML models	Using Chi-square feature set						Using PCA feature set
	Accu.	Prec	Rec.	Spec	F1-s	Time	Accu.	Prec.	Rec.	Spec	F1-s	Time
Logistic Regression	0.768	0.769	0.76	0.77	0.77	3.7	0.760	0.761	0.76	0.76	0.76	3.9
SVM	0.823	0.820	0.82	0.82	0.82	111.9	0.776	0.770	0.77	0.77	0.77	113.9
Decision Tree	0.639	0.647	0.64	0.69	0.63	14.6	0.637	0.673	0.63	0.54	0.65	10.2
KNN	0.778	0.822	0.73	0.67	0.72	6.3	0.782	0.819	0.77	0.72	0.77	7.6
Naive Bayes	0.698	0.699	0.69	0.69	0.69	2.75	0.697	0.664	0.67	0.65	0.66	3.3
Random Forest	0.888	0.886	0.89	0.89	0.88	4.3	0.793	0.781	0.72	0.70	0.72	4.8
Gradient Boosting	0.853	0.859	0.86	0.86	0.85	35.2	0.805	0.809	0.81	0.81	0.80	36.8
Adaptive Boosting	0.773	0.789	0.77	0.75	0.77	177.2	0.790	0.792	0.79	0.78	0.79	104.1
XG Boosting	0.783	0.779	0.77	0.74	0.77	75.2	0.765	0.769	0.76	0.74	0.76	86.8
CAT Boost	0.811	0.813	0.81	0.80	0.81	48.3	0.799	0.795	0.79	0.79	0.80	50.5