Comparar métodos

	Regras de Associação por Ensemble	Boosting
Área	Aprendizado de máquina	Aprendizado de máquina
Família	Machine learning	Machine learning
Ano de origem	late 1990s–2000s	1990–1997
Autor original	Various (applied ensemble philosophy from Breiman and others to association rule mining)	Schapire, R. E.; Freund, Y.
Tipo	Ensemble meta-learning over association rule learners	Sequential ensemble (iterative reweighting)
Fonte seminal	Domingos, P. (1999). MetaCost: A general method for making classifiers cost-sensitive. Proceedings of the 5th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 155–164.	Freund, Y. & Schapire, R. E. (1997). A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, 55(1), 119–139.
Outros nomes	Ensemble ARM, aggregated association rules, combined frequent-pattern mining, multi-run association rule learning	AdaBoost, gradient boosting, iterative reweighting ensemble, sequential ensemble
Relacionados	6	6
Resumo	Ensemble Association Rules applies ensemble learning principles to association rule mining: multiple rule sets are discovered from different data subsamples or with varied parameters, then merged and weighted to produce a more stable and complete set of co-occurrence patterns. The approach reduces sensitivity to support and confidence threshold choices and improves robustness on noisy transactional data.	Boosting is a sequential ensemble technique that converts many simple, barely-better-than-chance learners into a single highly accurate model by repeatedly focusing training on the examples that previous learners got wrong, then combining all learners with weights proportional to their individual accuracy.