Table 1 Fitting method and tuning parameter configurations. Provided are the considered training parameters for partial least squares (PLS), project pursuit (PPR), elastic net (ENet), support vector machine with a linear kernel (SVM-L), support vector machine with a radial basis function kernel (SVM-R), gradient boosting machine (GBM), and random forests (RF). Also provided are the model fitting methods

PLS

Number of components \(\in \{1,...,20\}\)

pls

PPR

Number of terms \(\in \{1,..,5\}\)

ppr

Enet

Mixing percentage \(\alpha \in \{0.10,0.55,1.00\}\)

glmnet

Penalty parameter \(\lambda \in \{8.975e^{-4},8.975e{^-3},8.975e^{-2}\}\)

SVM-L

Cost parameter \(\in \{0.001,0.002,...,0.02\}\)

svmLinear

SVM-R

Cost parameter \(\in \{5,...,20\}\)

svmRadialSigma

RBF kernel parameter \(\sigma \in \{0.0001,0.0005,...,0.02\}\)

GBM

Interaction depth \(\in \{1,...,5\}\)

gbm

Number of trees \(\in \{10,20,...,100\}\)

Shrinkage 0.1

Minimum number of Obs. in a node 10

RF

Number of randomly selected predictors \(\in \{1,...,10\}\)

rf