No abstract

No abstract

In recent years, more software engineering researchers have focussed on methods, techniques, tools, and processes to support software project management (SPM) addressing quality, cost, and time constraints. In this direction, the use of Bayesian belief networks (BBNs) has gained attention for providing a powerful mechanism for cause–effect analysis with both qualitative and quantitative data to support decision making under uncertainty. This work aims to provide an overview of the first 20 years of research in BBNs applied to SPM, and by so doing it contributes to the structuring of this research topic and the identification of new research opportunities. We conducted a systematic mapping (SM) study on the use of BBN as a decision‐support tool for SPM issues. We analysed over 109 relevant publications, from 1999 to 2018 (i.e., 20 years), to understand the motivations for using Bayesian networks (why), the problem domain and model scope addressed by researchers (what), the stage of the life cycle in which BBNs are being used (when), the venues of the publications (where), and the tools used to model the Bayesian networks (how). We draw the following conclusions from the results of our SM: (1) The application of Bayesian networks in SPM has been an active research topic since 1999. (2) Prediction and planning are the most common purposes in 60% of selected papers. (3) Software quality (55%) is the problem domain most investigated. (4) Most of the surveyed studies embrace the project (47%) and product (37%) scopes. And finally, (5) the development phase (86%) is when Bayesian networks have been more used. As future work, we highlight the need to further investigate methodologies that enable the use of BBNs in real software development contexts.

No abstract