Class imbalances versus small disjuncts
Top Cited Papers
- 1 June 2004
- journal article
- Published by Association for Computing Machinery (ACM) in ACM SIGKDD Explorations Newsletter
- Vol. 6 (1) , 40-49
- https://doi.org/10.1145/1007730.1007737
Abstract
It is often assumed that class imbalances are responsible for significant losses of performance in standard classifiers. The purpose of this paper is to the question whether class imbalances are truly responsible for this degradation or whether it can be explained in some other way. Our experiments suggest that the problem is not directly caused by class imbalances, but rather, that class imbalances may yield small disjuncts which, in turn, will cause degradation. We argue that, in order to improve classifier performance, it may, then, be more useful to focus on the small disjuncts problem than it is to focus on the class imbalance problem. We experiment with a method that takes the small disjunct problem into consideration, and show that, indeed, it yields a performance superior to the performance obtained using standard or advanced solutions to the class imbalance problem.Keywords
This publication has 5 references indexed in Scilit:
- The class imbalance problem: A systematic study1Intelligent Data Analysis, 2002
- Concept-Learning in the Presence of Between-Class and Within-Class ImbalancesPublished by Springer Nature ,2001
- Machine Learning for the Detection of Oil Spills in Satellite Radar ImagesMachine Learning, 1998
- Adaptive Fraud DetectionData Mining and Knowledge Discovery, 1997
- The Effects of Adding Noise During Backpropagation Training on a Generalization PerformanceNeural Computation, 1996