Decision Tree (page 2 of 5)

The general idea is to use a tree-like structure (with nodes and leaves) to minimize a loss function, which can lead to a better solution (especially when we have non-linear relationships between our features and our target).

A decision tree algorithm may be effective when: 1) There are not too many relevant features (less than thousands) and 2) We want to interpret the model to learn about your problem.