EasyDeepLearn

What makes CatBoost different from XGBoost / LightGBM?

hard

Answer

  • (1) Ordered boosting: uses a permutation of the data so that for each example, the model used to estimate its gradient is fit on other examples only — reduces prediction shift / target leakage that plagues target encoding in vanilla GBM.
  • (2) Native categorical support via ordered target statistics — handles high-cardinality categoricals without one-hot.
  • (3) Symmetric (oblivious) trees — same split at every node of a given depth, giving fast inference and implicit regularization.
  • (4) Good defaults — often the strongest 'out-of-the-box' GBDT.
Check yourself — multiple choice
  • It's the same as XGBoost with a rebranded name
  • Ordered boosting, native categorical support via ordered target stats, symmetric trees, strong defaults
  • It's only for classification
  • It removes the need for regularization

Ordered boosting + ordered target encoding + oblivious trees = CatBoost's identity.

#catboost#gradient-boosting#boosting#encoding

Practise Supervised Learning

215 interview questions in this topic.

Related questions