Back to GalleryRandom Forest
Random Forest builds an ensemble of independent Decision Trees. Each tree is trained on a random bootstrap sample of the dataset and a random subset of features. Predictions are made via majority voting across the ensemble.
Key Parameters & Visual Influence:
• Number of Trees: More trees produce smoother, more stable decision boundaries and reduce variance.
• Max Depth: Determines the complexity of individual trees. Higher depth permits intricate decision regions.
• Max Features: Limits evaluated features at each split, promoting tree diversity and decorrelating their predictions.
Dataset Studio
CSV format: Headers in first row, last column = label/target. All values must be numeric.
Example: x1, x2, label
Hyperparameters
Number of TreesTotal number of decision trees in the forest ensemble.10
150
Max Depth per TreeMaximum split depth allowed for any individual tree.4
112
Max FeaturesSize of feature subset evaluated at splits (Square Root, All, Log₂).
3 / 5 parameters active