Decision Tree
Single interpretable tree-based classifier
A Decision Tree builds a flowchart-like structure by repeatedly splitting data on the most informative feature. It is the most interpretable tree model but prone to overfitting without depth constraints.
When to use:
- When full interpretability and explainability are required
- Quick baseline model before trying ensembles
- Rule extraction for business logic
Input: Tabular data with the feature columns defined during training Output: Predicted class label and class probabilities
Model Settings (set during training, used at inference)
Max Depth (default: null — unlimited) Maximum tree depth. Constrain this to prevent overfitting — values of 3–10 are typical for production models.
Min Samples Split (default: 2) Minimum samples required to split a node. Higher values create simpler trees.
Min Samples Leaf (default: 1) Minimum samples in a leaf node. Increasing this smooths the model.
Criterion (default: gini)
Impurity measure. gini or entropy for classification.
Max Features (default: null — all features) Number of features to consider per split.
Class Weight (default: null)
Set to balanced for imbalanced datasets.
Inference Settings
No dedicated inference-time settings. Each input row follows the learned decision path.