SPE3DLAB can perform an unsupervised selection of predictors. This allows the identification of the leanest model out from a dataset with a lot of variables.
SPE3DLab uses the SuperLeaner algorithm to establish the best continuous variable prediction.
SPE3DLab displays the values of the specificity / sensitivity of the different models envisaged
SPE3dLab looks for the best gamma / cost couple based on the specificity and sensitivity of discrimination between groups taken two by two
SPE3DLab looks for the best gamma / cost torque based on the specificity and sensitivity of the discrimination between the two groups