Prediction of cost and defects in software development using bayesian and subspace algorithms

Abstract

Software Development is the discipline of initiating, organizing, executing, controlling and completing the project work of a group to accomplish target and meet progress. Prediction of software defects plays an important role while building high quality software. Machine learning algorithms are utilized in software development for better Performance. Machine learning algorithms have proven to be of great practical value in a variety of application domains. They are particularly useful for poorly understood problem domains where little learning exists to develop powerful algorithms and for the domains where there are expensive databases containing valuable implicit regularities to be discovered. Machine learning is a kind of Artificial Intelligence (AI) that enables programming applications to end up more exact in expectation results. The main objective of this paper is to predict the cost and defects of a project or an application in an efficient manner by applying machine learning algorithms. The Bayesian and subspace algorithms are implemented to predict the defects and to make decisions whether the project can be continued or not. Two algorithms are compared and the results are exhibited by applying on software defect data set.