DECISION TREES: 'Classification and Decision Trees'(CART) Divides the training set into rectangles (partitions) based on simple rules and a measure of 'impurity.' (recursive partitioning) Rules and partitions can be visualized as a 'tree.' These rules can then be used to classify new data sets.
(Adapted from ‘The Elements of Statistical Learning ‘ Hasti, Tibshirani,Friedman)
RANDOM FORESTS: An ensemble of decision trees.
CHI-SQUARED AUTOMATIC INTERACTION DETECTION: characterized by the use of a chi-square test to stop decision tree splits. (CHAID) Requires more computational power than CART.