Random Forest
Ensemble of decision trees for robust regression
Random Forest Regressor averages predictions from many decision trees trained on random data subsets. This reduces variance and produces stable predictions on noisy data.
When to use:
- General-purpose regression with good default performance
- Nonlinear relationships with mixed feature types
- When feature importance is needed
Input: Tabular data with the feature columns defined during training Output: Continuous predicted value (average of all trees)
Model Settings (set during training, used at inference)
N Estimators (default: 100) Number of trees. More trees improve stability.
Max Depth (default: null — unlimited) Maximum tree depth.
Max Features (default: 1.0)
Features considered per split. sqrt or log2 can reduce correlation between trees.
Min Samples Leaf (default: 1) Minimum samples per leaf. Higher values smooth predictions.
Bootstrap (default: true) Whether trees are built on bootstrap samples.
Inference Settings
No dedicated inference-time settings. Predictions are averaged across all trained trees.