Likelihood ratio equivalence and imbalanced binary classification

作者：

Highlights：

• A principled method for imbalanced classification is presented.

• The iff conditions for principled re-balancing are established.

• Informed two-step re-balancing techniques are introduced.

• Extensive examples support the analysis.

摘要

•A principled method for imbalanced classification is presented.•The iff conditions for principled re-balancing are established.•Informed two-step re-balancing techniques are introduced.•Extensive examples support the analysis.

论文关键词：Imbalance,Bregman divergences,Likelihood ratio,Informed re-balancing,Sample emphasis

论文评审过程：Received 17 July 2018, Revised 28 March 2019, Accepted 29 March 2019, Available online 29 March 2019, Version of Record 17 April 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.03.050