ABSTRACT
Decision Tree is a learning tool suitable for resolving classification
and data mining problems. The classification can simply be done
by asking a series of simple questions about the feature space.
Each time an answer is received, a follow-up question is then asked
until the conclusion about the class label can be achieved. Related
to some randomly selected features, the series of questions and
answers are organized in a tree structure. Its major advantage is
the ability to make fast decision with reference to an appropriately
trained tree structure. Using more than one tree forms a forest
structure, and in many cases multi forests are used. This is not a
chapter on a comprehensive survey of the subject area, but it gives
an introduction to the basic concepts of random tree and random
forests which form the materials supporting several other chapters
in this book. Realization details of three practical examples are
provided.
