Software Fault Prediction in Service-Oriented Based Systems

Software fault prediction plays a crucial role in enhancing software quality and minimizing maintenance cost. Primary goal of software fault prediction is to identify flaws before testing stage, that will save the expense and duration of software development while improving the software product's quality. In recent years, deep learning techniques have gained significant attention in the field of software fault prediction due to their ability to extract complex patterns and features from large-scale software datasets. This paper aims to provide a comprehensive overview of the existing research on software fault prediction using deep learning techniques. It covers a wide range of studies, including various deep learning models, feature engineering approaches, evaluation metrics, and datasets used in this domain. We examine strategies for predicting software faults in Service-Oriented Architecture based systems using deep learning and hybrid optimization-enabled deep learning methods. The findings reveal that hybrid deep learning and nature-inspired enabled deep learning techniques are more effective than just using machine learning and deep learning approaches.