3.2 Decision Tree Learning
Decision tree learning is a supervised learning technique aiming at the classification of instances based on predictor variables. There is one categorical response variable labeling the data and the result is arranged in the form of a tree. Figures 3.1, 3.2, and 3.3 show three decision trees computed for the data sets described earlier in this chapter. Leaf nodes correspond to possible values of the response variable. Non-leaf