The Static Model Of Data Mining Essay

1710 Words7 Pages
Abstract: Lot of research done in mining software repository. In this paper we discussed about the static model of data mining to extract defect .Different algorithms are used to find defects like naïve bayes algorithm, Neural Network, Decision tree. But Naïve Bayes algorithm has the best result .Data mining approach are used to predict defects in software .We used NASA dataset namely, Data rive. Software metrics are also used to find defects. Keywords: Naïve Bayes algorithm, Software Metric, Solution Architecture,. I. INTRODUCTION According to [1], multiple algorithms are combined to show better prediction capability using votes. Naïve Bayes algorithm gives the best result if used individual than others. The contribution of this paper based on two reasons. Firstly, it provides a solution architecture which is based on software repository and secondly it provides benchmarks that provide an ensemble of data mining models in the defective module prediction problem and compare the result. Author used NASA dataset online [2] which contain five large software projects with thousands of modules. Bohem found 80/20 rule and about the half modules are defect free [3]. Fixing Defects in the operational phase is considerably more expensive than doing so in the development or testing phase. Cost-escalation factors ranges from 5:1 to 100:1 [3]. It tells defects can be fixed in operational phase not in development and testing phase. The study of defect prediction can be classified into
Open Document