Decision Tree Regressor component - ClickML Studio

Decision Tree Regressor splits the training data into regions and predicts the mean target value within each region. It’s the most interpretable regression model.

Configuration

Parameter	Description	Default
Max Depth	Maximum tree depth. Shallower = less overfitting.	None
Min Samples Split	Minimum samples to split a node.	`2`
Min Samples Leaf	Minimum samples in a leaf node.	`1`
Criterion	Split quality measure: `squared_error`, `friedman_mse`, `absolute_error`, `poisson`	`squared_error`
Random State	Seed for reproducibility.	`42`

Input / Output

	Type
Input	`X Train` + `Y Train`
Output	Trained Model

When to use

Useful for understanding how predictions are made. Control Max Depth to prevent overfitting. Does not require feature scaling.