A method to build Bayesian networks based on artifacts and metrics to assess agile projects

Abstract

Managing software development projects is a complex task because it requires organizing and monitoring several activities. Recently, in order to assist on software projects management, artifact-based models were proposed in the literature. However, the current solutions do not present means to monitor projects health and assist on decisions making. Due to the recent popularization of agile methods, they are the units of study of this research. In this work, we present a method to build artifact and measurementbased models to assess agile projects health. We applied the method to build a generic model based on industrys best practice. We defined the models artifacts and metrics based on findings of a literature review and the assistance of an expert. For each models artifact, we applied the Goal-Question-Metric paradigm to define the metrics. Afterwards, from the GQM meta-model, we constructed a Bayesian network. We validated the model with simulated scenarios. Given the successful results, we concluded that the method and model are promising.