A search-based software engineering approach to support multiple team formation for scrum projects

Abstract

Search-Based software engineering (SBSE) deals with metaheuristic search-based optimization techniques to provide solutions for complex problems. A popular problem in literature is the team formation problem (TFP), which consists of finding the best allocation of human resources to a software development project. This problem is recognized as NP-hard and it is more complex in companies that carry out multiple projects. This paper presents an effective and automated approach to allocate multiple developers into multiple teams to maximize the technical compatibility between them. The approach consists of an SBSE method that uses Genetic Algorithm to simultaneously build multiple teams, using data from tag-based profiles. We conducted an empirical evaluation using data from eight realworld software projects of a Brazilian company. The results indicate that tag-based profiles is a promising information source to represent technical knowledge, since the suggested teams were considered to have the proper skills to the attend the technical demand of the projects. The approach was able to reach high levels of satisfaction, delivering teams in an effective and automated way. Although, further investigation needs to be conducted to reach stronger conclusions.