Table 4.

Possible hyperparameter choices for random forest. Ranges are integer intervals

	Possible values
Hyperparameter	Classification (Binary/Multiclass)	Regression
Max features to try	$[1,\dots ,⌊\sqrt{m}⌋]$	[1, …, ⌊m/3⌋]
Min samples to split node	[1, …, 11]
Min samples to be leaf node	[1, …, 11]
Number of trees	[25, …, 50]a
Impurity criterion	Gini index/Entropy	N/A

^aexcept UPDRS Part III total score, [64, …, 128]