An Efficient Software Defect Prediction Model Using Neuro Evalution Algorithm based on Genetic Algorithm

The main aim of Software Defect Prediction (SDP) is to identify the defect prone in source code, therefore to reduce the effort and time taken as well the cost incurred by it with guaranteeing the quality of software. The machine learning algorithms is used both code and non-code metrics are trained to predict software defects. This paper explores a knowledge of using code profiles as an alternative to traditional metrics to predict software defects. This proposed novel evolution algorithm proves to be more promising than any traditional machine learning approaches. The objective is to derive an efficient machine learning model that can predict the number of bugs the software project can produce while reaching the Quality Assurance (QA) Stage.