So sánh phương pháp

	XGBoost có thể giải thích	Gradient Boosting
Lĩnh vực	Học máy	Học máy
Họ	Machine learning	Machine learning
Năm ra đời	2016–2020	2001
Người khởi xướng	Chen & Guestrin (XGBoost); Lundberg & Lee (SHAP for trees)	Friedman, J. H.
Loại	Interpretable ensemble (gradient-boosted trees + SHAP)	Ensemble (sequential boosting of decision trees)
Công trình gốc	Lundberg, S. M., Erion, G., Chen, H., DeGrave, A., Prutkin, J. M., Nair, B., Katz, R., Himmelfarb, J., Bansal, N., & Lee, S.-I. (2020). From local explanations to global understanding with explainable AI for trees. Nature Machine Intelligence, 2(1), 56–67.	Friedman, J. H. (2001). Greedy Function Approximation: A Gradient Boosting Machine. Annals of Statistics, 29(5), 1189–1232.
Tên gọi khác	XGBoost + SHAP, interpretable XGBoost, XAI-XGBoost, transparent gradient boosting	Gradient Boosting (GBM), GBM, gradient boosted trees, gradient boosting machine
Liên quan	6	5
Tóm tắt	Explainable XGBoost pairs the high predictive accuracy of XGBoost gradient-boosted trees with SHAP (SHapley Additive exPlanations) values to make each prediction fully auditable. The result is a model that matches or surpasses neural networks on tabular data while offering theoretically grounded, per-prediction feature attributions that satisfy both scientific transparency and regulatory demands.	Gradient Boosting is an ensemble learning method, formalised by Jerome H. Friedman in 2001, that combines a sequence of weak learners — typically shallow decision trees — so that each new tree is fitted to minimise the residual errors of the trees before it. It is the core algorithm behind popular implementations such as XGBoost, LightGBM and CatBoost.