Model-Based Synthetic Sampling for Imbalanced Data

Chien-Liang Liu*, Po-Yen Hsieh

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

63 Scopus citations

Abstract

Imbalanced data is characterized by the severe difference in observation frequency between classes and has received a lot of attention in data mining research. The prediction performances usually deteriorate as classifiers learn from imbalanced data, as most classifiers assume the class distribution is balanced or the costs for different types of classification errors are equal. Although several methods have been devised to deal with imbalance problems, it is still difficult to generalize those methods to achieve stable improvement in most cases. In this study, we propose a novel framework called model-based synthetic sampling (MBS) to cope with imbalance problems, in which we integrate modeling and sampling techniques to generate synthetic data. The key idea behind the proposed method is to use regression models to capture the relationship between features and to consider data diversity in the process of data generation. We conduct experiments on thirteen datasets and compare the proposed method with ten methods. The experimental results indicate that the proposed method is not only comparative but also stable. We also provide detailed investigations and visualizations of the proposed method to empirically demonstrate why it could generate good data samples.
Original languageEnglish
Pages (from-to)1543-1556
Number of pages14
JournalIEEE Transactions on Knowledge and Data Engineering
Volume32
Issue number8
DOIs
StatePublished - 1 Aug 2020

Fingerprint

Dive into the research topics of 'Model-Based Synthetic Sampling for Imbalanced Data'. Together they form a unique fingerprint.

Cite this