Table 8.

Wilcoxon signed-rank test results comparing classifier pairs on validation set metrics across all datasets.

ALC vs.	Dataset	P-value
		Loss	Accuracy	Overfitting	Time
XGB	Iris Flower	0.432	0.872	0.481	0.493
SVM	Iris Flower	0.012	0.950	0.008	0.025
MLP	Iris Flower	0.006	0.951	0.021	0.001
LR	Iris Flower	0.037	0.042	0.029	0.017
XGB	Breast Cancer	0.004	0.015	0.007	0.970
SVM	Breast Cancer	0.001	0.009	0.013	0.064
MLP	Breast Cancer	0.015	0.011	0.012	0.004
LR	Breast Cancer	0.000	0.020	0.001	0.005
XGB	Wine	0.022	0.763	0.012	0.974
SVM	Wine	0.893	0.004	0.706	0.002
MLP	Wine	0.005	0.681	0.023	0.003
LR	Wine	0.031	0.822	0.748	0.002
XGB	Voice Gender	0.011	0.019	0.005	0.951
SVM	Voice Gender	0.000	0.002	0.007	0.001
MLP	Voice Gender	0.851	0.804	0.029	0.002
LR	Voice Gender	0.019	0.781	0.003	0.001
XGB	MNIST	0.001	0.014	0.004	0.993
SVM	MNIST	0.003	0.043	0.012	0.945
MLP	MNIST	0.001	0.017	0.008	0.936
LR	MNIST	0.002	0.041	0.009	0.898