방법 비교

	설명 가능한 LightGBM	SHAP (SHapley Additive exPlanations)
분야	머신러닝	머신러닝
계열	Machine learning	Machine learning
기원 연도	2017	2017
창시자	Ke, G. et al. (LightGBM); Lundberg, S. M. & Lee, S.-I. (SHAP for tree models)	Lundberg, S.M. & Lee, S.-I.
유형	Gradient boosting with post-hoc explainability (SHAP)	Model-explanation method (Shapley-value attribution)
원전	Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30, 4765–4774.	Lundberg, S.M. & Lee, S.-I. (2017). A Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing Systems, 30, 4766–4777.
별칭	XAI-LightGBM, LightGBM with SHAP, Interpretable LightGBM, LightGBM explainability	SHAP Değerleri (Model Açıklanabilirlik), Shapley additive explanations, SHAP values, model explainability
관련	6	5
요약	Explainable LightGBM combines Microsoft's LightGBM gradient boosting framework with SHAP (SHapley Additive exPlanations) to deliver both high predictive performance and rigorous, theoretically grounded feature-level explanations. It is widely adopted in applied research where predictive accuracy and interpretability are simultaneously required.	SHAP is a model-explanation method, introduced by Scott Lundberg and Su-In Lee in 2017, that uses Shapley values from cooperative game theory to measure how much each feature contributes to an individual prediction, making the output of black-box machine-learning models interpretable. It supports both global explanations (overall feature importance) and local explanations (why one specific prediction came out the way it did).