Bayesian network based bug-fix effort prediction model

Abstract

Development and use of prediction model (process performance models, PPM) are the primary requirements of high maturity practices. PPMs are useful tools for project management and process management. They help project managers to predict process performance with a known level of confidence thereby enabling them identify the risk and take actions. Over a last few years, Bayesian Belief Networks (BBN) have received a great deal of attention as prediction models, since they provide better solution to some of the problems found in Software Engineering when compared with traditional statistical models. In this paper, we are presenting our experience of using BBN for bug-fix effort prediction. © 2012 Springer-Verlag.