LightGBM, Light Gradient Boosting Machine
==========




LightGBM is a gradient boosting framework that using histogram based tree learning algorithm. It can outperform existing boosting tools on both learning speed and accuracy. Our [experiments](https://github.com/Microsoft/LightGBM/wiki/Experiments#comparison-experiment) shows it is about 6x faster than xgboost with much better prediction accuracy.

LightGBM can be run on multiple machines, Our [experiments](https://github.com/Microsoft/LightGBM/wiki/Experiments#parallel-experiment) shows it can perform linear speed up in parallel learning. 

* [**Wiki**](https://github.com/Microsoft/LightGBM/wiki)
* [**Installation**](https://github.com/Microsoft/LightGBM/wiki/Installation-Guide) 
* [**Quick Start**](https://github.com/Microsoft/LightGBM/wiki/Quick-Start)
* [**Feature Highlight**](https://github.com/Microsoft/LightGBM/wiki/Feature-Highlight) 
* [**Parallel Learning Guide**](https://github.com/Microsoft/LightGBM/wiki/Parallel-Learning-Guide) 
* [**Parameters**](https://github.com/Microsoft/LightGBM/wiki/Parameters) 
* [**Examples**](https://github.com/Microsoft/LightGBM/tree/master/examples)