MAHAKIL: Diversity based Oversampling Approach to Alleviate the Class Imbalance Issue in Software Defect Prediction

Kwabena Ebo Bennin, Jacky Keung, Passakorn Phannachitta, Akito Monden, Solomon Mensah

Research output: Contribution to journalArticle

36 Citations (Scopus)

Abstract

Highly imbalanced data typically make accurate predictions difficult. Unfortunately, software defect datasets tend to have fewer defective modules than non-defective modules. Synthetic oversampling approaches address this concern by creating new minority defective modules to balance the class distribution before a model is trained. Notwithstanding the successes achieved by these approaches, they mostly result in over-generalization (high rates of false alarms) and generate near-duplicated data instances (less diverse data). In this study, we introduce MAHAKIL, a novel and efficient synthetic oversampling approach for software defect datasets that is based on the chromosomal theory of inheritance. Exploiting this theory, MAHAKIL interprets two distinct sub-classes as parents and generates a new instance that inherits different traits from each parent and contributes to the diversity within the data distribution. We extensively compare MAHAKIL with SMOTE, Borderline-SMOTE, ADASYN, Random Oversampling and the No sampling approach using 20 releases of defect datasets from the PROMISE repository and five prediction models. Our experiments indicate that MAHAKIL improves the prediction performance for all the models and achieves better and more significant pf values than the other oversampling approaches, based on Brunner's statistical significance test and Cliff's effect sizes. Therefore, MAHAKIL is strongly recommended as an efficient alternative for defect prediction models built on highly imbalanced datasets.

Original languageEnglish
JournalIEEE Transactions on Software Engineering
DOIs
Publication statusAccepted/In press - Jul 25 2017

    Fingerprint

Keywords

  • Animals
  • Biological cells
  • Class imbalance learning
  • Classification problems
  • Data sampling methods
  • Electronic mail
  • Predictive models
  • Sampling methods
  • Software
  • Software defect prediction
  • Synthetic sample generation

ASJC Scopus subject areas

  • Software

Cite this