Software fault prediction is a critical task in software engineering that aims to identify and prevent faults in software code before they occur.Machine learning algorithms have been shown to be effective in this area, providing accurate and timely predictions of software faults.In this research paper, we examine the effectiveness of different machine learning algorithms for software fault prediction using publicly available datasets.We compare the performance of four popular machine learning algorithms, namely support vector machines (SVM), random forests (RF), k-nearest neighbors (KNN), and Nave Bayes (NB), using various metrics such as accuracy, precision, recall, and F1-score.We also perform feature selection to identify the most relevant features for each algorithm.In conclusion, our research highlights the effectiveness of machine learning algorithms for software fault prediction and provides insights into the most suitable algorithm for specific datasets.By leveraging the power of machine learning algorithms, software developers can effectively predict and prevent software faults.These findings provide a reference point that can be used to evaluate the effectiveness and advancements of any novel approaches in software defect prediction.
Authors: Jayanti Goyal, Ripu Ranjan Sinha
DOI: https://doi.org/10.30696/jac.xvii.1.2023.9-16
Publish Year: 2023
