A Hybrid Model of Soft Computing Technique for Software Fault Prediction

Software fault prediction plays a vital role in software quality assurance, identifying the faulty modules to better concentrate on those modules and helps to improve the quality of the software. With increasing complexity of software now a day’s feature selection is important to remove the redundant, irrelevant and erroneous data from the dataset. In general, Feature selection is done mainly based on filter and wrapper .In this paper wrapper method for feature selection is used, and various machine learning techniques (Neural gas, SVM classifier), Symbolic Regression(genetic programming) and ABC algorithm are used. Artificial Bee Colony algorithm is considered new and widely used in searching for optimum solutions. ABC proved to be a suitable candidate for classification tasks, which gives a better prediction than the traditional methods. NASA’s public dataset KC1 and PC1 available at promise software engineering repository is used. And also MUSHROOM dataset taken from the Audubon Society Field to evaluate the performance of the software fault prediction models Accuracy value are used. Software development has become an essential investment for many organizations. Software engineering practitioners have become more and more concerned about accurately predicting the fault and quality of software under development. Accurate estimates are desired but no model has proved to be successful at effectively and consistently predicting software fault.