MACHINE LEARNING BASED HYBRID APPROACH FOR SOFTWARE DEFECT PREDICTION
Main Article Content
Abstract
Ensuring software reliability is a critical challenge in the tech industry, traditionally addressed through manual inspection and experience-based techniques that can be time-consuming and inefficient. Automated software defect prediction models, leveraging machine learning, offer a proactive solution to identify and mitigate defects early in the development cycle. This study proposes a defect prediction model based on hybrid learning techniques, evaluating its performance against Decision Trees (DT), Naïve Bayes (NB), Artificial Neural Networks (ANN), and Support Vector Machines (SVM). Using standard evaluation metrics such as ten-fold cross-validation, precision, recall, specificity, F1-score, and accuracy, our findings demonstrate that hybrid learning consistently outperforms other models, achieving classification accuracy between 98% and 100% across multiple datasets (JM1, CM1, and PC1). While DT also performs well, NB and ANN require careful tuning, and SVM exhibits the lowest accuracy. These results highlight hybrid learning as a robust and effective approach for enhancing software reliability by improving defect prediction accuracy.
Downloads
Article Details
COPYRIGHT
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.