CatBoost: gradient boosting with categorical features support

TL;DR

CatBoost is a new open-source gradient boosting library that effectively handles categorical features, offers GPU and CPU implementations, and outperforms existing libraries in quality and speed on popular datasets.

Contribution

Introduces CatBoost, a gradient boosting library with native categorical feature support and optimized GPU/CPU implementations, improving performance and efficiency.

Findings

Outperforms existing gradient boosting libraries in quality.

Faster training and scoring on large ensembles.

Effective handling of categorical features.

Abstract

In this paper we present CatBoost, a new open-sourced gradient boosting library that successfully handles categorical features and outperforms existing publicly available implementations of gradient boosting in terms of quality on a set of popular publicly available datasets. The library has a GPU implementation of learning algorithm and a CPU implementation of scoring algorithm, which are significantly faster than other gradient boosting libraries on ensembles of similar sizes.