Table 8.

Hyperparameters of the optimal classifiers built on base data set used for the calculation of tenfold cross-validation accuracy in Table 7. The “with D” and “no D” columns refer to the full and reduced (after removal of D) sets of features, respectively. N/A stands for “Not Applicable” (the first two parameters are random forest specific). The definitions of the feature sets are given in Table 1.

Features	Model	Variant	Bootstrap	Criterion	max_depth	max_features	min_samples_leaf	min_samples_split	n_estimators
Set A	RF	with D	True	gini	80	sqrt	4	2	800
		no D	True	entropy	10	sqrt	2	10	600
	GB	with D	N/A	N/A	50	sqrt	4	10	900
		no D	N/A	N/A	10	log2	2	2	100
Set B	RF	with D	True	entropy	None	None	2	5	1000
		no D	True	entropy	None	log2	1	10	600
	GB	with D	N/A	N/A	110	log2	2	10	400
		no D	N/A	N/A	10	log2	4	5	100
Set C	RF	with D	True	entropy	60	log2	4	2	900
		no D	True	entropy	10	sqrt	2	10	600
	GB	with D	N/A	N/A	10	log2	2	2	100
		no D	N/A	N/A	10	log2	2	2	100