AI-Driven Software Defect Prediction Using Machine Learning

J. David Sukeerthi Kumar, K. Ruthesha, D. V. Akshitha, G. Himavarshini, U. Manasa

2025

Abstract

Defect prediction in software is a well-documented problem in the software engineering. To be successful in software development, it must be related software engineering and data mining. Prediction of defects will assist in identification of faults in the source code, before testing. Different methodologies, like clustering, statistical technique, neural network, black-box testing, white-box testing and machine learning are utilized for predicting of defects. This research proposed feature selection for enhancing the accuracy of machine learning classifiers in defect prediction. The goal is to increase the forecasting accuracy with five publicly available NASA scenarios: CM1, JM1, KC2, KC1, and PC1. Feature Selection is combined to a variety of ML algorithms such as Random Forest, Logistic Regression, Multilayer Perceptron, Bayesian Networks, Rule ZeroR, J48, Lazy IBK, Support Vector Machines, Neural Networks, Decision Stump. Data pre-processing and model deployment is carried out using WEKA (Waikato Environment for Knowledge Analysis) data insisting while statistical analysis is done through Minitab. The outcome shows that it becomes impressive using facet alternative (WFS) in improving defect prediction accuracies when in contrast to the models which there isn't any facet alternative (WOFS).

Paper Citation

in Harvard Style

Kumar J., Ruthesha K., Akshitha D., Himavarshini G. and Manasa U. (2025). AI-Driven Software Defect Prediction Using Machine Learning. In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - Volume 1: ICRDICCT`25; ISBN 978-989-758-777-1, SciTePress, pages 850-856. DOI: 10.5220/0013874500004919

in Bibtex Style

@conference{icrdicct`2525,
author={J. Kumar and K. Ruthesha and D. Akshitha and G. Himavarshini and U. Manasa},
title={AI-Driven Software Defect Prediction Using Machine Learning},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - Volume 1: ICRDICCT`25},
year={2025},
pages={850-856},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013874500004919},
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 - Volume 1: ICRDICCT`25
TI - AI-Driven Software Defect Prediction Using Machine Learning
SN - 978-989-758-777-1
AU - Kumar J.
AU - Ruthesha K.
AU - Akshitha D.
AU - Himavarshini G.
AU - Manasa U.
PY - 2025
SP - 850
EP - 856
DO - 10.5220/0013874500004919
PB - SciTePress