XGBoost baseline model for classification
XGBoost baseline model for regression
<aside> 💡 Algorithm can handle missing values. This is true for all Gradient Boost based models. See also this post.
</aside>
XGBoost stands for eXtreme Gradient Boosting. It is an open-source project that is not part of Scikit-learn, though it has recently been expanded by a Scikit-learn wrapper interface that makes it easier to incorporate XGBoost into a Scikit-learn-style data pipeline.
The algorithm has always retained a strong appeal among the community of data scientists, though it struggled to keep pace with the innovation brought about by other GBM implementations such as LightGBM and CatBoost.
Aside from good performance both in terms of accuracy and computational efficiency, XGBoost is also a scalable solution, using at best multi-core processors as well as distributed machines.
XGBoost vs CatBoost vs LightGBM
XGBoost and imbalanced datasets