August 24, 2025International Journal For Multidisciplinary Research

A comparative study of machine learning algorithm for software defect prediction

View Full Paper

Ask AI

Bookmark

Improved accuracy results from hybrid models integrating various machine learning techniques, enhancing defect prediction.
The hybrid machine learning model includes Random Forest, SVM, CNN, and Logistic Regression for superior performance.
Analysis utilizes multiple machine learning algorithms to assess prediction accuracy for software defects, suggesting advancements over traditional methods.
Results underline the importance of integrating diverse machine learning algorithms in software defect prediction approaches.

Implication

This comparative study finds improved accuracy in software defect prediction using hybrid machine learning models, including SVM and CNN.

Abstract

Software defects are among the leading causes of software failure, causing performance degradation, increased costs, and compromised reliability. This research introduces a hybrid machine learning-based SDP model that integrates Random Forest, Support Vector Machines (SVM), Convolutional Neural Networks (CNN), and Logistic Regression to predict software bugs with improved accuracy.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Vijay Yadav (2025) studied this question.

synapsesocial.com/papers/68af5bc1ad7bf08b1eadfc84 https://doi.org/10.36948/ijfmr.2025.v07i04.53768

View Full Paper

Ask AI

Bookmark

Implication

This comparative study finds improved accuracy in software defect prediction using hybrid machine learning models, including SVM and CNN.

A comparative study of machine learning algorithm for software defect prediction

Key Points

Implication

Abstract

Discussion

Cite This Study

A comparative study of machine learning algorithm for software defect prediction

Key Points

Implication

Abstract

Discussion

Cite This Study

Keep reading

Keep reading