An AIS based feature selection method for software fault prediction

Software fault prediction plays a vital role in software quality assurance. Identifying the faulty modules helps to well concentrate on those modules and helps improve the quality of the software. With increasing complexity of software nowadays 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, an AIS based feature selection method is proposed to make a better prediction in comparison with the traditional ones. NASA´s public dataset KC1 available at promise software engineering repository is used. Results show that the selected subset of features increases the accuracy of classifier from 82.44% to 83.72% which is better than other methods results.