A simple plug-in bagging ensemble based on threshold-moving for classifying binary and multiclass imbalanced data
Name
1-s2.0-S092523121731456X-main.pdf
Size
1.49 MB
Format
Adobe PDF
Checksum (MD5)
cfdc20baf9c165c565db0b9042b0a7e1
Author(s)
Collell Talleda, Guillem
Prelec, Drazen
Patil, Kaustubh R
Date Issued
September 2017
Journal
Neurocomputing
Publisher
Elsevier BV
Citation
Collell, Guillem et al. “A Simple Plug-in Bagging Ensemble Based on Threshold-Moving for Classifying Binary and Multiclass Imbalanced Data.” Neurocomputing 275 (January 2018): 330–340 © 2017 The Author(s)
Version
Final published version
Abstract
Class imbalance presents a major hurdle in the application of classification methods. A commonly taken approach is to learn ensembles of classifiers using rebalanced data. Examples include bootstrap averaging (bagging) combined with either undersampling or oversampling of the minority class examples. However, rebalancing methods entail asymmetric changes to the examples of different classes, which in turn can introduce their own biases. Furthermore, these methods often require specifying the performance measure of interest a priori, i.e., before learning. An alternative is to employ the threshold moving technique, which applies a threshold to the continuous output of a model, offering the possibility to adapt to a performance measure a posteriori, i.e., a plug-in method. Surprisingly, little attention has been paid to this combination of a bagging ensemble and threshold-moving. In this paper, we study this combination and demonstrate its competitiveness. Contrary to the other resampling methods, we preserve the natural class distribution of the data resulting in well-calibrated posterior probabilities. Additionally, we extend the proposed method to handle multiclass data. We validated our method on binary and multiclass benchmark data sets by using both, decision trees and neural networks as base classifiers. We perform analyses that provide insights into the proposed method. Keywords: Imbalanced data; Binary classification; Multiclass classification; Bagging ensembles; Resampling; Posterior calibration
MIT Department
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Massachusetts Institute of Technology. Department of Economics
Sloan School of Management
Terms of Use
Creative Commons Attribution 4.0 International license
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1016/J.NEUCOM.2017.08.035
