So sánh phương pháp

	Gradient Boosting Giải thích được	Cây quyết định giải thích được
Lĩnh vực	Học máy	Học máy
Họ	Machine learning	Machine learning
Năm ra đời	2017–2020	1984 (CART); XAI framing formalized 2010s–2020s
Người khởi xướng	Lundberg, S. M. & Lee, S.-I. (TreeSHAP for tree ensembles)	Breiman, L.; Friedman, J.; Olshen, R. A.; Stone, C. J.
Loại	Ensemble + explainability layer	Interpretable supervised learning model
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, 56–67.	Breiman, L., Friedman, J., Olshen, R. A., & Stone, C. J. (1984). Classification and Regression Trees. Wadsworth & Brooks/Cole. ISBN: 978-0-412-04841-8
Tên gọi khác	XGB with SHAP, interpretable gradient boosting, transparent gradient boosting, XAI gradient boosting	XDT, interpretable decision tree, rule-based decision tree, transparent decision tree
Liên quan	6	4
Tóm tắt	Explainable Gradient Boosting combines the predictive power of gradient boosting ensembles with structured interpretability tools — principally SHAP (SHapley Additive exPlanations) — to produce models that are both highly accurate and transparently auditable. Practitioners obtain global feature rankings and individual-level explanations alongside standard performance metrics.	An Explainable Decision Tree is a classification or regression tree deliberately grown to be shallow, readable, and auditable — producing a finite set of if-then rules that a human can verify without additional tools. It sits at the intersection of predictive modelling and Explainable AI (XAI), chosen when stakeholders must understand and trust every prediction the model makes.