Software quality prediction using machine learning

Abstract

BackgroundThe demand for software is increasing every day in various fields. Software developers put more effort to develop and test the quality of the software and verify its reliability before it is released. High-quality software modules were developed to allow others to reuse the components. Purpose: This paper provides information to researchers in the software quality prediction field based on machine learning algorithms. Methodology: Most of the machine learning techniques and the relevant software metrics used in many high-quality papers published between 2010 and the end of 2021 have been analysed. Findings: Machine learning techniques are the most suitable for predicting software quality. Most of the researchers' interest was to predict the reliability of software. The detailed analysis enables researchers to choose the best way to plan their research and to make a good contribution in the field of software quality prediction.