Table 3.

5-fold cross validation mean squared error (MSE) for continuous models trained on oversampled training data using linear, random forest, deep neural network (DNN) and ordinal regression, and random forest and DNN split classification.

Model	Continuous MSE	Ordinal MSE
Linear regression	0.450+0.002	0.541+0.002
Random forest regression	0.240+0.001	0.305+0.002
DNN regression	0.441+0.015	0.532+0.016
Ordinal regression	0.450+0.002	0.539+0.001
Random forest split classifiers	0.260+0.001	0.279+0.001
DNN split classifiers	0.541+0.021	0.574+0.024