Development of recommendation systems for software engineering: the CROSSMINER experience

Abstract To perform their daily tasks, developers intensively make use of existing resources by consulting open source software (OSS) repositories. Such platforms contain rich data sources, e.g., code snippets, documentations, and user discussions, that can be useful for supporting development activities. Over the last decades, several techniques tools have been promoted to provide with innovative features, aiming bring in improvements terms effort, cost savings, productivity. In context EU H2020 CROSSMINER project, a set recommendation systems has conceived assist programmers different phases process. The various artifacts, such as third-party libraries, documentation about how APIs being adopted, or relevant API function calls. develop recommendations, technical choices made overcome issues related aspects including lack baselines, limited availability, decisions performance measures, evaluation approaches. This paper is an experience report present knowledge pertinent developed through project. We explain detail challenges we had deal with, together lessons learned when developing evaluating these systems. Our aim research community concrete takeaway messages are expected those who want customize own reported experiences facilitate interesting discussions work, which end contribute advancement applied solve Software Engineering.