Table 9.

Holdout mean squared error (MSE) for continuous models trained on original 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	Cohen’s Kappa
Linear regression	0.285	0.356	0.413
Random forest regression	0.264	0.332	0.446
Deep neural network regression	0.326	0.408	0.409
Ordinal regression	0.285	0.356	0.413
Random forest split classifiers	0.285	0.317	0.476
Deep neural network split classifiers	0.304	0.350	0.416