Bagged Flexible Discriminant Analysis

method = 'bagFDA'

Type: Classification

Tuning Parameters: degree (Product Degree), nprune (#Terms)

Bagged MARS

method = 'bagEarth'

Type: Regression, Classification

Tuning Parameters: nprune (#Terms), degree (Product Degree)

Boosted Classification Trees

method = 'ada'

Type: Classification

Tuning Parameters: iter (#Trees), maxdepth (Max Tree Depth), nu (Learning Rate)

Boosted Generalized Additive Model

method = 'gamboost'

Type: Regression, Classification

Tuning Parameters: mstop (# Boosting Iterations), prune (AIC Prune?)

Boosted Linear Model

method = 'bstLs'

Type: Regression, Classification

Tuning Parameters: mstop (# Boosting Iterations), nu (Shrinkage)

Boosted Logistic Regression

method = 'LogitBoost'

Type: Classification

Tuning Parameters: nIter (# Boosting Iterations)

Boosted Smoothing Spline

method = 'bstSm'

Type: Regression, Classification

Tuning Parameters: mstop (# Boosting Iterations), nu (Shrinkage)

C4.5-like Trees

method = 'J48'

Type: Classification

Tuning Parameters: C (Confidence Threshold)

C5.0

method = 'C5.0'

Type: Classification

Tuning Parameters: trials (# Boosting Iterations), model (Model Type), winnow (Winnow)

CART

method = 'rpart'

Type: Regression, Classification

Tuning Parameters: cp (Complexity Parameter)

CART

method = 'rpart2'

Type: Regression, Classification

Tuning Parameters: maxdepth (Max Tree Depth)

Conditional Inference Random Forest

method = 'cforest'

Type: Classification, Regression

Tuning Parameters: mtry (#Randomly Selected Predictors)

Conditional Inference Tree

method = 'ctree'

Type: Classification, Regression

Tuning Parameters: mincriterion (1 - P-Value Threshold)

Conditional Inference Tree

method = 'ctree2'

Type: Regression, Classification

Tuning Parameters: maxdepth (Max Tree Depth)

Cost-Sensitive C5.0

method = 'C5.0Cost'

Type: Classification

Tuning Parameters: trials (# Boosting Iterations), model (Model Type), winnow (Winnow), cost (Cost)

Cost-Sensitive CART

method = 'rpartCost'

Type: Classification

Tuning Parameters: cp (Complexity Parameter), Cost (Cost)

Cubist

method = 'cubist'

Type: Regression

Tuning Parameters: committees (#Committees), neighbors (#Instances)

Elasticnet

method = 'enet'

Type: Regression

Tuning Parameters: fraction (Fraction of Full Solution), lambda (Weight Decay)

Flexible Discriminant Analysis

method = 'fda'

Type: Classification

Tuning Parameters: degree (Product Degree), nprune (#Terms)

Generalized Linear Model with Stepwise Feature Selection

method = 'glmStepAIC'

Type: Regression, Classification

No Tuning Parameters

glmnet

method = 'glmnet'

Type: Regression, Classification

Tuning Parameters: alpha (Mixing Percentage), lambda (Regularization Parameter)

Least Angle Regression

method = 'lars'

Type: Regression

Tuning Parameters: fraction (Fraction)

Least Angle Regression

method = 'lars2'

Type: Regression

Tuning Parameters: step (#Steps)

Logistic Model Trees

method = 'LMT'

Type: Classification

Tuning Parameters: iter (# Iteratons)

Model Rules

method = 'M5Rules'

Type: Regression

Tuning Parameters: pruned (Pruned), smoothed (Smoothed)

Model Tree

method = 'M5'

Type: Regression

Tuning Parameters: pruned (Pruned), smoothed (Smoothed), rules (Rules)

Multivariate Adaptive Regression Spline

method = 'earth'

Type: Regression, Classification

Tuning Parameters: nprune (#Terms), degree (Product Degree)

Multivariate Adaptive Regression Splines

method = 'gcvEarth'

Type: Regression, Classification

Tuning Parameters: degree (Product Degree)

Nearest Shrunken Centroids

method = 'pam'

Type: Classification

Tuning Parameters: threshold (Shrinkage Threshold)

Oblique Random Forest

method = 'ORFlog'

Type: Classification

Tuning Parameters: mtry (#Randomly Selected Predictors)

Oblique Random Forest

method = 'ORFpls'

Type: Classification

Tuning Parameters: mtry (#Randomly Selected Predictors)

Oblique Random Forest

method = 'ORFridge'

Type: Classification

Tuning Parameters: mtry (#Randomly Selected Predictors)

Oblique Random Forest

method = 'ORFsvm'

Type: Classification

Tuning Parameters: mtry (#Randomly Selected Predictors)

Oblique Trees

method = 'oblique.tree'

Type: Classification

Tuning Parameters: oblique.splits (Oblique Splits), variable.selection (Variable Selection Method)

Parallel Random Forest

method = 'parRF'

Type: Classification, Regression

Tuning Parameters: mtry (#Randomly Selected Predictors)

Penalized Linear Discriminant Analysis

method = 'PenalizedLDA'

Type: Classification

Tuning Parameters: lambda (L1 Penalty), K (#Discriminant Functions)

Penalized Linear Regression

method = 'penalized'

Type: Regression

Tuning Parameters: lambda1 (L1 Penalty), lambda2 (L2 Penalty)

Quantile Random Forest

method = 'qrf'

Type: Regression

Tuning Parameters: mtry (#Randomly Selected Predictors)

Random Ferns

method = 'rFerns'

Type: Classification

Tuning Parameters: depth (Fern Depth)

Random Forest

method = 'rf'

Type: Classification, Regression

Tuning Parameters: mtry (#Randomly Selected Predictors)

Random Forest by Randomization

method = 'extraTrees'

Type: Regression, Classification

Tuning Parameters: mtry (# Randomly Selected Predictors), numRandomCuts (# Random Cuts)

Regularized Random Forest

method = 'RRF'

Type: Regression, Classification

Tuning Parameters: mtry (#Randomly Selected Predictors), coefReg (Regularization Value), coefImp (Importance Coefficient)

Regularized Random Forest

method = 'RRFglobal'

Type: Regression, Classification

Tuning Parameters: mtry (#Randomly Selected Predictors), coefReg (Regularization Value)

Relaxed Lasso

method = 'relaxo'

Type: Regression

Tuning Parameters: lambda (Penalty Parameter), phi (Relaxation Parameter)

Rule-Based Classifier

method = 'JRip'

Type: Classification

Tuning Parameters: NumOpt (# Optimizations)

Rule-Based Classifier

method = 'PART'

Type: Classification

Tuning Parameters: threshold (Confidence Threshold), pruned (Confidence Threshold)

Single C5.0 Ruleset

method = 'C5.0Rules'

Type: Classification

No Tuning Parameters

Single C5.0 Tree

method = 'C5.0Tree'

Type: Classification

No Tuning Parameters

Single Rule Classification

method = 'OneR'

Type: Classification

No Tuning Parameters

Sparse Linear Discriminant Analysis

method = 'sparseLDA'

Type: Classification

Tuning Parameters: NumVars (# Predictors), lambda (Lambda)

Sparse Mixture Discriminant Analysis

method = 'smda'

Type: Classification

Tuning Parameters: NumVars (# Predictors), lambda (Lambda), R (# Subclasses)

Stacked AutoEncoder Deep Neural Network

method = 'dnn'

Type: Classification, Regression

Tuning Parameters: layer1 (Hidden Layer 1), layer2 (Hidden Layer 2), layer3 (Hidden Layer 3), hidden_dropout (Hidden Dropouts), visible_dropout (Visible Dropout)

Stochastic Gradient Boosting

method = 'gbm'

Type: Regression, Classification

Tuning Parameters: n.trees (# Boosting Iterations), interaction.depth (Max Tree Depth), shrinkage (Shrinkage)

The lasso

method = 'lasso'

Type: Regression

Tuning Parameters: fraction (Fraction of Full Solution)

Tree Models from Genetic Algorithms

method = 'evtree'

Type: Regression, Classification

Tuning Parameters: alpha (Complexity Parameter)

Tree-Based Ensembles

method = 'nodeHarvest'

Type: Regression, Classification

Tuning Parameters: maxinter (Maximum Interaction Depth), mode (Prediction Mode)