CatBoost: unbiased boosting with categorical features

Code

• github.com/catboost/catboost
  OfficialIn papernone★ 0
• github.com/yumoh/catboost_iter
  none★ 1
• github.com/anantgupta129/CatBoost-in-Python-ML
  none★ 0
• github.com/sswetank-CS/MIL
  none★ 0
• github.com/xiadanqing/Binary
  none★ 0
• github.com/vj-thakur/catboost
  none★ 0
• github.com/kazeevn/catboost
  none★ 0
• github.com/hananlibpost/ml_final_project
  none★ 0
• github.com/sgsonu/SoftBank-Forex-Algorithm-Challenge
  none★ 0
• github.com/jiangzhongkai/ifly-algorithm_challenge
  none★ 0

Abstract

This paper presents the key algorithmic techniques behind CatBoost, a new gradient boosting toolkit. Their combination leads to CatBoost outperforming other publicly available boosting implementations in terms of quality on a variety of datasets. Two critical algorithmic advances introduced in CatBoost are the implementation of ordered boosting, a permutation-driven alternative to the classic algorithm, and an innovative algorithm for processing categorical features. Both techniques were created to fight a prediction shift caused by a special kind of target leakage present in all currently existing implementations of gradient boosting algorithms. In this paper, we provide a detailed analysis of this problem and demonstrate that proposed algorithms solve it effectively, leading to excellent empirical results.

Tasks

Reproductions