@inproceedings{23ba1c3c247c4636823a2416809c8b89,
title = "Ensemble Learning with Resampling for Imbalanced Data",
abstract = "Imbalanced class distribution is an issue that appears in various applications. In this paper, we undertake a comprehensive study of the effects of sampling on the performance of bootstrap aggregating in the context of imbalanced data. Concretely, we carry out a comparison of sampling methods applied to single and ensemble classifiers. The experiments are conducted on simulated and real-life data using a range of sampling methods. The contributions of the paper are twofold: i) demonstrate the effectiveness of ensemble techniques based on resampled data over a single base classifier and ii) compare the effectiveness of different resampling techniques when used during the bagging stage for ensemble classifiers. The results reveal that ensemble methods overwhelmingly outperform single classifiers based on resampled data. In addition, we discover that NearMiss and random oversampling (ROS) are the optimal sampling algorithms for ensemble learning.",
keywords = "Data preprocessing sampling, Ensemble method, Imbalanced data, Oversampling, Undersampling",
author = "Firuz Kamalov and Ashraf Elnagar and Leung, {Ho Hon}",
note = "Publisher Copyright: {\textcopyright} 2021, Springer Nature Switzerland AG.; 17th International Conference on Intelligent Computing, ICIC 2021 ; Conference date: 12-08-2021 Through 15-08-2021",
year = "2021",
doi = "10.1007/978-3-030-84529-2_48",
language = "English",
isbn = "9783030845285",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "564--578",
editor = "De-Shuang Huang and Kang-Hyun Jo and Jianqiang Li and Valeriya Gribova and Abir Hussain",
booktitle = "Intelligent Computing Theories and Application - 17th International Conference, ICIC 2021, Proceedings",
}