Improving Software Defect Prediction Accuracy Using Machine Learning

J. David Sukeerthi Kumar, Shaik Mithaigiri Mohammad Akram, Mulinti Abhinay, Desam Pavan Kumar, Shaik Mansoor Hussain, Ponnaganti Bharath Kumar

2025

Abstract

Software defect prediction plays an important role in enhancing software quality by detecting potential problems at an early stage of the development life cycle. Traditional methods rely upon the time-consuming, and often faulty, static analysis and manual code reviews. Machine learning (ML) offers a powerful alternative that uses historical defect data to enhance the prediction of defect-prone modules. In this project, we experiment with different types of ML methods including supervised learning techniques like Random Forest, Decision Trees, SVM, and Deep Learning models to solve the task. We utilize feature engineering, data prepossessing and model optimization to improve prediction performance. In this paper, the project discusses various models to see how effectively various types of models can predict software defects when tested on commonly used software defect datasets and measures their success with appropriate metrics such as precision & recall and F1-score the proposed method helps to improve accuracy in defect prediction, maintain software, lower maintenance cost, and improve reliability of software system.

Paper Citation

in Harvard Style

Kumar J., Akram S., Abhinay M., Kumar D., Hussain S. and Kumar P. (2025). Improving Software Defect Prediction Accuracy Using Machine Learning. In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25; ISBN 978-989-758-777-1, SciTePress, pages 844-854. DOI: 10.5220/0013906700004919

in Bibtex Style

@conference{icrdicct`2525,
author={J. Kumar and Shaik Akram and Mulinti Abhinay and Desam Kumar and Shaik Hussain and Ponnaganti Kumar},
title={Improving Software Defect Prediction Accuracy Using Machine Learning},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25},
year={2025},
pages={844-854},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013906700004919},
isbn={978-989-758-777-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25
TI - Improving Software Defect Prediction Accuracy Using Machine Learning
SN - 978-989-758-777-1
AU - Kumar J.
AU - Akram S.
AU - Abhinay M.
AU - Kumar D.
AU - Hussain S.
AU - Kumar P.
PY - 2025
SP - 844
EP - 854
DO - 10.5220/0013906700004919
PB - SciTePress