Foundations of Imbalanced Learning
Gary M. Weiss · 2013
This chapter provides an understanding of the foundations of imbalanced learning by providing a clear description of the relevant issues, and a clear mapping of these issues to the methods that can be used to address them. This mapping is quite important as many research papers on imbalanced learning fail to provide a comprehensive description of how or why these methods work, and what underlying issue(s) they address. These issues are divided into: problem-definition-level issues, data-level issues and algorithm-level issues. The chapter concludes with a discussion on the misconceptions about sampling methods. Sampling methods are the most common methods for dealing with imbalanced data, but yet there are widespread misconceptions related to these methods. The most basic misconception concerns the notion that sampling methods are equivalent to certain other methods for dealing with class imbalance. This issue must be considered much more carefully in future studies. Controlled Vocabulary Terms learning (artificial intelligence); sampling methods