Table 4.

Accuracy of the best classifiers trained on the base data set (see Table 2) with Set A of features. The “with D” and “no D” columns refer to the full and reduced (after removal of D) sets of features, respectively. The results are rounded to three decimal digits.

	Random Forest		Gradient Boosting
Data Set	With D	No D	With D	No D
Training	0.979	0.962	1.0	0.993
Test	0.957	0.955	0.956	0.955