Decision Trees

Decision trees, either classification or regression trees, are especially attractive type of models for three main reasons: Firstly, They have an intuitive representation; the resulting model is easy to understand and assimilate by humans. Secondly, the decision trees are nonparametric models, no intervention being required from the user, and thus they are very suited for exploratory knowledge discovery. Finally, Performance degrades gracefully with the increase in the size of training data. Formally, one can define a decision tree to be either: a leaf node or a nonleaf node that contains an attribute test with a branch to another decision tree for each possible value of the attribute. A decision tree can be seen as a divide‐and‐conquer strategy for object classification. The best‐known method of decision trees generation is the top‐down induction of decision trees (TDIDT) algorithm. For binary decision trees, the border between two neighboring regions of different classes is known as a decision boundary.