Learning Effective Changes for Software Projects
This addresses the planning task for software developers and managers, offering clear guidance on actions to take, but it is incremental as it builds on existing prediction-focused tools.
The authors tackled the problem of moving beyond prediction to actionable planning in software analytics by proposing XTREE and BELLTREE algorithms, which generate plans that improve software project quality.
The primary motivation of much of software analytics is decision making. How to make these decisions? Should one make decisions based on lessons that arise from within a particular project? Or should one generate these decisions from across multiple projects? This work is an attempt to answer these questions. Our work was motivated by a realization that much of the current generation software analytics tools focus primarily on prediction. Indeed prediction is a useful task, but it is usually followed by "planning" about what actions need to be taken. This research seeks to address the planning task by seeking methods that support actionable analytics that offer clear guidance on what to do. Specifically, we propose XTREE and BELLTREE algorithms for generating a set of actionable plans within and across projects. Each of these plans, if followed will improve the quality of the software project.