Comparer des méthodes

	Généralisation empilée	Vote Pondéré
Domaine	Apprentissage ensembliste	Prise de décision
Famille	Machine learning	MCDM
Année d'origine	1992	1951
Auteur d'origine	David Wolpert	Arrow, K. J.
Type	meta-learning aggregation	Social choice — weighted positional voting rule
Source fondatrice	Wolpert, D. H. (1992). Stacked generalization. Neural Networks, 5(2), 241-259.	Arrow, K. J. (1951). Social Choice and Individual Values. Wiley, New York
Alias	stacking, meta-learning	—
Apparentées	3	0
Résumé	Stacked generalization, or stacking, is a two-level ensemble method where base-level classifiers are trained on the original data, and a meta-learner is trained on the predictions of the base classifiers. The meta-learner learns how to best combine base predictions rather than using fixed aggregation rules. Introduced by David Wolpert in 1992, stacking achieves state-of-the-art performance by automatically learning the optimal weighting and interaction patterns among base models.	WEIGHTED-VOTING (Weighted Voting — Weighted positional aggregation of multiple rankings) is a ranking multi-criteria decision-making (MCDM) method introduced by Arrow, K. J. in 1951. It turns a decision matrix of alternatives scored on multiple criteria into a structured, reproducible result.