Sun, Q. & Pfahringer, B. (2011). Bagging ensemble selection. In Lecture Notes in Computer Science, 2011, Volume 7106, AI 2011: Advances in Artificial Intelligence. Pp. 251-260.
Permanent Research Commons link: http://hdl.handle.net/10289/6366
Ensemble selection has recently appeared as a popular ensemble learning method, not only because its implementation is fairly straightforward, but also due to its excellent predictive performance on practical problems. The method has been highlighted in winning solutions of many data mining competitions, such as the Netix competition, the KDD Cup 2009 and 2010, the UCSD FICO contest 2010, and a number of data mining competitions on the Kaggle platform. In this paper we present a novel variant: bagging ensemble selection. Three variations of the proposed algorithm are compared to the original ensemble selection algorithm and other ensemble algorithms. Experiments with ten real world problems from diverse domains demonstrate the benefit of the bagging ensemble selection algorithm.
This is the author's accepted version. The original publication is available at www.springerlink.com. Copyright Springer-Verlag Berlin Heidelberg 2011.