Enhancing Bug Prediction with Machine Learning Algorithms

Authors

  • T. Bhaskar
  • Avanti Joshi
  • Kiran Nikam
  • Pagar Pratibha
  • Nale Divyani

Abstract

Software Bug Prediction (SBP) enhances software quality by identifying defects early and reducing maintenance efforts and costs. Accurate bug prediction models help improve the overall software development process, but building an effective model remains challenging due to the complex nature of software systems.

This research explores the performance of five machine learning algorithms K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Random Forest, Decision Tree, and Naïve Bayes in predicting software bugs. Our results indicate that Random Forest outperforms the others, achieving an accuracy of 93.7%, precision of 91.5%, recall of 92.1%, and an F1 score of 91.8%. KNN follows closely with an accuracy of 90.8%, while Naïve Bayes delivers the lowest results with 66.1% accuracy.

These findings confirm that machine learning techniques, particularly Random Forest, offer significant promise for improving software defect prediction, providing a reliable and scalable method for enhancing the software development lifecycle.

Downloads

Published

2024-12-23

How to Cite

Bhaskar, T., Joshi, A., Nikam, K., Pratibha, P., & Divyani, N. (2024). Enhancing Bug Prediction with Machine Learning Algorithms. Journal of Hacking Techniques, Digital Crime Prevention and Computer Virology, 1(3), 50–61. Retrieved from https://matjournals.net/engineering/index.php/JoHTDCPCV/article/view/1246

Issue

Volume 1 Issue 3 (December 2024)

Section

Articles