Knowledge-aware recommender system for software development

Open source software (OSS) forges contain rich data sources that are useful for the development process. We promote techniques and tools for providing open source developers with innovative features aiming at obtaining improvements in terms of development effort, cost savings, developer productivity. Our work is a coherent paradigm that facilitates multiple recommendations to assist software developers in different phases of the development process. In the scope of this paper, we introduce a graph-based representation to encode in a homogeneous manner different aspects of the OSS ecosystem. Furthermore, we develop a knowledge-aware recommender system for providing developers with suitable API function calls. An initial evaluation on real datasets shows that the system is able to produce relevant API calls.