1 Copyright © 2010, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited. Chapter 1 Software Project and Quality Modelling Using Bayesian Networks Norman Fenton Queen Mary, University of London, United Kingdom Peter Hearty Queen Mary, University of London, United Kingdom Martin Neil Queen Mary, University of London, United Kingdom Łukasz Radliński Queen Mary, University of London, United Kingdom, and University of Szczecin, Poland INTRODUCTION Software project planning is notoriously unreliable. Attempts to predict the effort, cost and quality of software projects have foundered for many rea- sons. These include the amount of effort involved in collecting metrics, the lack of crucial data, the subjective nature of some of the variables involved and the complex interaction of the many variables which can affect a software project. In this chapter we introduce Bayesian Networks (BNs) and show how they can overcome these problems. We cover sufficient BN theory to enable the reader to construct and use BN models using a suit- able tool, such as AgenaRisk (Agena Ltd. 2008). From this readers will acquire an appreciation for the ease with which complex, yet intuitive, statistical models can be built. The statistical nature of BN models automatically enables them to deal with the ABSTRACT This chapter provides an introduction to the use of Bayesian Network (BN) models in Software Engineering. A short overview of the theory of BNs is included, together with an explanation of why BNs are ideally suited to dealing with the characteristics and shortcomings of typical software development environments. This theory is supplemented and illustrated using real world models that illustrate the advantages of BNs in dealing with uncertainty, causal reasoning and learning in the presence of limited data. DOI: 10.4018/978-1-60566-758-4.ch001