DefectGRANDE: Hybrid Approach for Class Imbalance in Software Defect Prediction

Eunjeong Ju; Jeonghwa Lee; Duksan Ryu

doi:10.1109/BigComp64353.2025.00025

DefectGRANDE: Hybrid Approach for Class Imbalance in Software Defect Prediction

Eunjeong Ju
, Jeonghwa Lee
, Duksan Ryu^*

^*Corresponding author for this work

Jeonbuk National University

Research output: Contribution to journal › Conference article › peer-review

1 Scopus citations

Abstract

Software Defect Prediction (SDP) ensures software quality by identifying defects early in development. However, a major challenge is class imbalance, where defect data is vastly outnumbered by non-defect data, reducing prediction accuracy. To address this, we propose DefectGRANDE, a hybrid model leveraging SMOTE for data balancing, RandomForest for feature importance, and ensemble learning for stability. DefectGRANDE outperforms existing methods in metrics like Positive Detection (PD), Balance, and AUC. Through this, defects can be predicted more effectively in the early stages of development, enhancing software quality and reliability while reducing development costs and time.

Original language	English
Pages (from-to)	90-91
Number of pages	2
Journal	Proceedings of the IEEE International Conference on Big Data and Smart Computing, BIGCOMP
Issue number	2025
DOIs	https://doi.org/10.1109/BigComp64353.2025.00025
State	Published - 2025
Event	2025 IEEE International Conference on Big Data and Smart Computing, BigComp 2025 - Kota Kinabalu, Malaysia Duration: 2025.02.9 → 2025.02.12

Keywords

class imbalance
data resampling
gradient-based optimization
software defect prediction

Quacquarelli Symonds(QS) Subject Topics

Computer Science & Information Systems
Data Science

Access to Document

10.1109/BigComp64353.2025.00025

Cite this

@article{094a1d1398be4d7e8bad161271d2ea33,

title = "DefectGRANDE: Hybrid Approach for Class Imbalance in Software Defect Prediction",

abstract = "Software Defect Prediction (SDP) ensures software quality by identifying defects early in development. However, a major challenge is class imbalance, where defect data is vastly outnumbered by non-defect data, reducing prediction accuracy. To address this, we propose DefectGRANDE, a hybrid model leveraging SMOTE for data balancing, RandomForest for feature importance, and ensemble learning for stability. DefectGRANDE outperforms existing methods in metrics like Positive Detection (PD), Balance, and AUC. Through this, defects can be predicted more effectively in the early stages of development, enhancing software quality and reliability while reducing development costs and time.",

keywords = "class imbalance, data resampling, gradient-based optimization, software defect prediction",

author = "Eunjeong Ju and Jeonghwa Lee and Duksan Ryu",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 2025 IEEE International Conference on Big Data and Smart Computing, BigComp 2025 ; Conference date: 09-02-2025 Through 12-02-2025",

year = "2025",

doi = "10.1109/BigComp64353.2025.00025",

language = "English",

pages = "90--91",

journal = "Proceedings of the IEEE International Conference on Big Data and Smart Computing, BIGCOMP",

issn = "2375-933X",

number = "2025",

}

TY - JOUR

T1 - DefectGRANDE

T2 - 2025 IEEE International Conference on Big Data and Smart Computing, BigComp 2025

AU - Ju, Eunjeong

AU - Lee, Jeonghwa

AU - Ryu, Duksan

PY - 2025

Y1 - 2025

N2 - Software Defect Prediction (SDP) ensures software quality by identifying defects early in development. However, a major challenge is class imbalance, where defect data is vastly outnumbered by non-defect data, reducing prediction accuracy. To address this, we propose DefectGRANDE, a hybrid model leveraging SMOTE for data balancing, RandomForest for feature importance, and ensemble learning for stability. DefectGRANDE outperforms existing methods in metrics like Positive Detection (PD), Balance, and AUC. Through this, defects can be predicted more effectively in the early stages of development, enhancing software quality and reliability while reducing development costs and time.

AB - Software Defect Prediction (SDP) ensures software quality by identifying defects early in development. However, a major challenge is class imbalance, where defect data is vastly outnumbered by non-defect data, reducing prediction accuracy. To address this, we propose DefectGRANDE, a hybrid model leveraging SMOTE for data balancing, RandomForest for feature importance, and ensemble learning for stability. DefectGRANDE outperforms existing methods in metrics like Positive Detection (PD), Balance, and AUC. Through this, defects can be predicted more effectively in the early stages of development, enhancing software quality and reliability while reducing development costs and time.

KW - class imbalance

KW - data resampling

KW - gradient-based optimization

KW - software defect prediction

UR - https://www.scopus.com/pages/publications/105006493137

U2 - 10.1109/BigComp64353.2025.00025

DO - 10.1109/BigComp64353.2025.00025

M3 - Conference article

AN - SCOPUS:105006493137

SN - 2375-933X

SP - 90

EP - 91

JO - Proceedings of the IEEE International Conference on Big Data and Smart Computing, BIGCOMP

JF - Proceedings of the IEEE International Conference on Big Data and Smart Computing, BIGCOMP

IS - 2025

Y2 - 9 February 2025 through 12 February 2025

ER -

DefectGRANDE: Hybrid Approach for Class Imbalance in Software Defect Prediction

Abstract

Keywords

Quacquarelli Symonds(QS) Subject Topics

Access to Document

Other files and links

Fingerprint

Cite this