Maintenance process modeling and dynamic estimations based on Bayesian networks and association rules

Managing the maintenance process and estimating accurately the effort and duration required for a new release is considered to be a crucial task as it affects successful software project survival and progress over time. In this study, we propose the combination of two well‐known machine learning (ML) techniques, Bayesian networks (BNs), and association rules (ARs) for modeling the maintenance process by identifying the relationships among the internal and external quality metrics related to a particular project release to both the maintainability of the project and the maintenance process indicators (ie, effort and duration). We also exploit Bayesian inference, to test the effect of certain changes in internal and external project factors to the maintainability of a project. We evaluate our approach through a case study on 957 releases of five open source JavaScript applications. The results show that the maintainability of a release, the changes observed between subsequent releases, and the time required between two releases can be accurately predicted from size, complexity, and activity metrics. The proposed combined approach achieves higher accuracy when evaluated against the BN model accuracy.