catboost/catboost

Free

A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports computation on CPU and GPU.

FreeFree tier

Type

Open Source

Visit Website GitHub (38 stars)

About catboost/catboost

CatBoost is an open-source machine learning library based on gradient boosting over decision trees. It is designed for high performance, scalability, and speed, supporting ranking, classification, regression, and other machine learning tasks. CatBoost offers best-in-class prediction speed, native support for both numerical and categorical features without preprocessing, fast training on CPU and GPU (including multi-GPU), built-in visualization tools, and reproducible distributed training via Apache Spark and CLI. It provides APIs for Python, R, Java, and C++, making it accessible for a wide range of data science and engineering workflows.

Key Features

Superior quality compared with other GBDT libraries on many datasets

Best-in-class prediction speed

Native support for numerical and categorical features without manual encoding

Fast GPU and multi-GPU training out of the box

Built-in visualization tools for model analysis

Fast and reproducible distributed training with Apache Spark and CLI

APIs for Python, R, Java, and C++

Pros & Cons

Pros

Open source with Apache-2.0 license
High performance and scalable gradient boosting
Handles categorical features automatically
Works on CPU and GPU (including multi-GPU)
Includes visualization and distributed training capabilities

Best For

Ranking tasksClassification problemsRegression analysisGeneral machine learning model development and deployment