Conceptualization and Development of ML-based Recommender Systems for Software Engineering
Recommender systems for software engineering (RSSEs) are complex software systems that suggest relevant items of interest according to the application domain, e.g., code snippets, Q&A posts, and third-party libraries. The development of RSs encompasses the execution of different steps, including data preprocessing, choice of appropriate algorithms, and item delivery, to name a few. Though RSs can alleviate the curse of information overload, existing approaches resemble black-box systems, where the end-user is not supposed to customize the overall process. The goal of this talk is twofold. First, I present developed RSSEs for two specific tasks, i.e., OSS project categorization and recommendation of modeling artifacts. Afterward, I discuss an MDE-based tool that simplifies the design, optimization, and deployment of recommender systems, making them more accessible to those without prior expertise.
Friday, October 20, 2023
@11h30
1207, Pav. André-Aisenstadt