Table 2.

Comparison of modeling techniques ranked from best to worst based on RMSE values. Both the standard deviation of the predictions and the standard deviation of the difference between predictions and the actual values (Standard Deviation of Residuals) are shown along with the ensemble weighting factors.

Model	RMSE	Standard Deviation	Standard Deviation of Residuals	Mean	Weighting Factor for Custom Ensemble
Custom Ensemble – Regression Weighting	15.30	6.39	15.30	19.41	(Intercept of 0.613)
GBM	15.32	6.47	15.31	19.38	0.620
Linear Regression	15.38	6.80	18.35	19.47	0.118
Random Forests	15.63	6.77	15.63	19.43	0.057
Decision Trees	15.81	4.84	15.81	19.45	0.096
SVM	15.82	5.89	15.39	14.59	0.158