A Review on Software Defect Prediction Using Machine Learning

Software plays an important role in many of the systems and devices that make up our modern societies. In order to provide their customers with software of a higher quality in a shorter amount of time, numerous software companies are developing software systems of varying sizes for various purposes. It is too challenging to produce high-quality software in a shorter amount of time due to the constraints of software development and the growing size of software data. Therefore, prior to delivering the software product, defect prediction can significantly contribute to a project's success in terms of; cost and quality to evaluate the quality of their software. The goal of the literature review is to investigate about the current trends of software defect prediction approaches. Conclusion of the literature review introduce that many machine learning algorithms are implemented named with Random forest, Logistic regression, Naïve Bayes and Artificial neutral Network etc. with different software metrics like CK metrics, Source code metric etc. The performance measurement of the model done by various methods like accuracy, precision etc.