Combining Bagging and Boosting

• DOI: 10.5281/zenodo.1059761
• Publication Date: 2007-08-28
• Authors: Sotiris Kotsiantis; Panagiotis Pintelas
• Keywords: Boosting

Bagging and boosting are among the most popular re- sampling ensemble methods that generate combine a diversity of classifiers using same learning algorithm for base-classifiers. Boosting algorithms considered stronger than bagging on noise- free data. However, there strong empirical indications is much more robust in noisy settings. For this reason, work we built an voting methodology ensembles with 10 sub- each one. We performed comparison simple 25 sub-classifiers, as well other known combining methods, standard benchmark datasets proposed technique was accurate.