Title

An Oversampling Technique for Classifying Imbalanced Datasets

Authors

Son Nguyen, Bryant UniversityFollow
John Quinn, Bryant UniversityFollow
Alan Olinsky, Bryant UniversityFollow

Document Type

Book Chapter

Comments

Is part of Advances in Business Management Forecasting.

Keywords

oversampling; imbalanced data; rare events; classification; SMOTE; sensitivity

Identifier Data

https://doi.org/10.1108/S1477-407020170000012004

Publisher

Emerald Insight

Publication Source

Advances in Business and Management Forecasting, Volume 13

Abstract

We propose an oversampling technique to increase the true positive rate (sensitivity) in classifying imbalanced datasets (i.e., those with a value for the target variable that occurs with a small frequency) and hence boost the overall performance measurements such as balanced accuracy, G-mean and area under the receiver operating characteristic (ROC) curve, AUC. This oversampling method is based on the idea of applying the Synthetic Minority Oversampling Technique (SMOTE) on only a selective portion of the dataset instead of the entire dataset. We demonstrate the effectiveness of our oversampling method with four real and simulated datasets generated from three models.