XGBoost is an open-source, scalable gradient-boosting library renowned for its speed, accuracy, and support for parallel, distributed and GPU-accelerated training.
LightGBM is an open-source gradient-boosting framework that delivers fast, memory-efficient tree-based learning for classification, regression and ranking tasks.
Open-source gradient-boosting library from Yandex that natively handles categorical features and offers fast CPU/GPU training.
