What is Decision Trees?
Decision trees is a non parametric supervised learning technique, which is used in classification and regression. It main goal is to predict the value of a given target variables by learning decision rules using data. It has a structure that consists of root node, branches, internal nodes and leaf nodes.
As displayed in the figure, the decision tree start with root node, then the algorithm select the feature which split the data well and use measures like Gini index. And it directly feed into the internal nodes (decision nodes). Based on available features internal nodes conduct evaluation to form leaf nodes (terminal nodes). Finally, leaf nodes represent all the results within the data sets.
For an example, a decision tree of weather will classify it, whether to play football based on condition like temperature and outlook. When the model’s structure become more and more clear that make it useful for prediction and better decision making.
