The completion of partial configurations might represent an expensive computational task. Existing solutions, such as those which use modern constraint satisfaction solvers, perform a complete search, which can be time-consuming and resource-intensive. This research activity aims to develop a novel approach to automate the completion of partial configurations, leveraging advanced techniques such as machine learning and optimization methods. The goal is to provide a scalable and efficient solution for completing partial configurations, enabling faster and more accurate results. By automating this process, we can reduce the computational burden and make it more feasible for large-scale applications.