Abstract
Software Product Line (SPL) configuration practices have been employed by industries as a mass customization process. However, the inherent variability of large SPLs leads to configuration spaces of exponential sizes. Thus, scalability and performance concerns start to be an issue when facing runtime environments, since it is usually infeasible to explore the entire configuration space exhaustively. In this context, the aim of my research is therefore to propose an efficient collaborative-based runtime approach that relies on recommender techniques to provide accurate and scalable configurations to users. To demonstrate the efficiency of the proposed approach, I conduct series of experiments on real-world SPLs. In addition, I plan empirically verify through a user case study the usability of the proposed approach. My expected contribution is to support the adoption of SPL configuration practices in industrial scenarios.