Suggesting Software Measurement Plans with Unsupervised Learning Data Analysis

Software measurement processes require to consider more and more data, measures and metrics. Measurement plans become complex, time and resource consuming, considering diverse kinds of software project phases. Experts in charge of defining the measurement plans have to deal with management and performance constraints to select the relevant metrics. They need to take into account a huge number of data though distributed processes. Formal models and standards have been standardized to facilitate some of these aspects. However, the maintainability of the measurements activities is still constituted of complex activities. In this paper, we aim at improving our previous work, which aims at reducing the number of needed software metrics when executing measurement process and reducing the expertise charge. Based on unsupervised learning algorithm, our objective is to suggest software measurement plans at runtime and to apply them iteratively. For that purpose, we propose to generate automatically analysis models using unsupervised learning approach in order to efficiently manage the efforts, time and resources of the experts. An implementation has been done and integrated on an industrial platform. Experiments are processed to show the scalability and effectiveness of our approach. Discussions about the results have been provided. Furthermore, we demonstrate that the measurement process performance could be optimized while being effective, more accurate and faster with reduced expert intervention.