BoostARoota
A fast feature selection algorithm for tree-based models like XGBoost, designed to outperform Boruta in speed and performance.
What is BoostARoota?
BoostARoota is a fast feature selection algorithm designed for tree-based machine learning models like XGBoost. It solves the problem of slow and inefficient feature selection in high-dimensional datasets by creating shadow features and iteratively removing unimportant variables. The algorithm significantly reduces computation time while maintaining or improving model performance compared to alternatives like Boruta.
Data scientists and machine learning engineers working with high-dimensional datasets who need efficient feature selection for tree-based models like XGBoost or sklearn classifiers.
Developers choose BoostARoota because it offers a 100x speed improvement over Boruta, supports flexible sklearn integration, and provides robust feature importance estimation through configurable parameters. Its optimized removal process ensures better performance on modern algorithms where traditional methods fall short.
Overview
A fast xgboost feature selection algorithm
Use Cases
Best For
- Speeding up feature selection for XGBoost models on large datasets
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
