Mastering Machine Learning with scikit-learn - Second Edition

Advantages and disadvantages of decision trees

The compromises associated with using decision trees are different from those of the other models we have discussed. Decision trees are easy to use. Unlike many learning algorithms, decision trees do not require the data to be standardized. While decision trees can tolerate missing values for features, scikit-learn's current implementation cannot. Decision trees can learn to ignore featuresthat are not relevant to the task, and can be used to determine which features are most useful.Decision trees support multi-output tasks, and a single decision tree can be used for multi-class classification without employing a strategy like one versus all.Small decision trees can be easy to interpret and visualize ...