Decision Trees

By the end, you'll be able to:

  • Explain how a decision tree turns feature tests into predictions.
  • Compare the main impurity criteria used to choose a split.
  • Control model complexity with stopping rules and pruning.
  • Tree anatomy: nodes, branches, and leaves
  • Axis-aligned partitions of the feature space
  • Classification error, Gini index, and entropy
  • Split gain and leaf predictions
  • Pre-pruning, post-pruning, and cost-complexity pruning
  • Categorical variables and computational considerations
Introduction & Partitioning