What is XGBoost?
XGBoost is a software library that stands for extreme gradient boosting. The library is an implementation of gradient boosting machines created by Tianqi Chen as a research project, and since contributed to by other developers. XGBoost focuses on computational speed and model performance, offering optimization features such as Gradient Boosting, Stochastic Gradient Boosting, and Regularized Gradient Boosting.
The XGBoost algorithm was implemented to maximize the efficiency of compute time and memory resources. The algorithm features Sparse Aware implementation by automatically handling missing values from data sets. Additionally, the algorithm allows for continued training of an already fitted model on new data.
XGBoost is a popular open source software library due mainly to the fact that it is really fast. Compared to other methods of gradient boosting, XGBoost consistently
performs faster than implementations from Python, Spark, and R. The developers aim to provide a "Scalable, Portable, and Distributed Gradient Boosting Library."
