> ML_ALGORITHM // RANDOM-FORESTS_v1.0
Random Forests
Ensemble learning method that builds hundreds of decorrelated decision trees on bootstrap subsets with random feature sampling.
Tree & Rule Ensemblesclassical-supervisedmoderate-posthocmedium (1k-100k)
Back to All AlgorithmsComputational Complexity
Training Complexity:O(n_trees * p_sample * n log n)
Inference Complexity:O(n_trees * depth)
Hardware Profile
CPU Friendly:Yes
Requires GPU:No
Memory Footprint:moderate
Interpretability & Data
Interpretability Tier:moderate-posthoc
Training Data Needs:medium (1k-100k)
Interpretability Assessment
Aggregated ensemble cannot be read as a single tree; relies on MDI, MDA, and SHAP values.
Suitable Tasks & Supported Modalities
Suitable Tasks:
binary classificationmulticlass classificationregressionanomaly detection
Supported Modalities:
tabular
Implementing Libraries
Foundational Literature
Random ForestsLeo Breiman (2001) · Machine Learning
Common Pitfalls & Warnings
- Default Gini importance biased toward high-cardinality categorical features
- Substantial RAM footprint when saving thousands of unpruned trees