A decomposition approach to imbalanced classification
- 1 July 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 258-260
Abstract
An important characteristic of many modern systems is the availability of large amounts of event data, collected through various sensors. Certain events occur very rarely among these, but may be critical to a successfully functioning system. Examples of these include faulty products, credit card frauds, among others. In this paper, we propose a framework for solving this problem, of detecting rare events, when modeled as a supervised learning task. Specifically, we consider an imbalanced 2-class classification problem. We overcome the challenge of class imbalance by decomposing the original learning task into many simpler learning tasks. A useful feature of the proposed algorithm is that the decision rule is simple enough to infer the importance of individual covariates in rare event detection. We present performance results on some public datasets to demonstrate the effectiveness of the proposed algorithm.Keywords
This publication has 10 references indexed in Scilit:
- Statistical Methods for Fighting Financial CrimesTechnometrics, 2010
- A classification procedure for highly imbalanced class sizesIIE Transactions, 2010
- COG: local decomposition for rare class analysisData Mining and Knowledge Discovery, 2010
- Remote sensing‐based neural network mapping of tsunami damage in Aceh, IndonesiaDisasters, 2007
- Fault Region Localization: Product and Process Improvement Based on Field Performance and Manufacturing MeasurementsIEEE Transactions on Automation Science and Engineering, 2006
- Extreme re-balancing for SVMsACM SIGKDD Explorations Newsletter, 2004
- Learning from imbalanced data sets with boosting and data generationACM SIGKDD Explorations Newsletter, 2004
- Mining needle in a haystack2001
- MetaCost1999
- Machine Learning for the Detection of Oil Spills in Satellite Radar ImagesMachine Learning, 1998