Recommender Systems for Software Developers

Software systems are becoming more and more complex, forcing developers to cope with the implementation, maintenance and evolution of millions of lines of code. Without assistance, developers can be easily overwhelmed by the amount of information, requirements, and constraints they have to deal with. Recommender systems can assist developers in a wide range of activities, such as optimizing non-functional requirements, producing documentation, and learning new technologies. For example, they can recommend refactoring operations to improve code maintainability, changes aimed at reducing the energy consumption of mobile apps, as well as tutorials useful to learn a new technology.

In this talk I will present recommender systems developed in the context of my research activity, by discussing the main challenges faced during their design and empirical evaluation. I will also highlight future directions for the field.

Gabriele Bavota is an Assistant Professor at the Free University of Bozen-Bolzano, Italy. He received the PhD degree in computer science from the University of Salerno, Italy, in 2013. From January 2013 to October 2014 he has been research fellow at the University of Sannio, Italy. 

His research interests include software maintenance, empirical software engineering, mining software repository, refactoring of software systems, and recommender systems. On these topics he co-authored over 70 papers appeared in international journals, conferences and workshops. He received 3 ACM Distinguished Paper Awards (ASE'13, ESEC/FSE'15, and ICSE'15), 1 Best Paper Award (SCAM'12), and 3 Distinguished Reviewer Awards (WCRE'12, SANER'15, and MSR'15).

He serves as a Program Co-Chair for ICPC'16, SCAM'16, and SANER'17. He also serves and has served as organizing and program committee member of international conferences in the field of software engineering, such as ICSE, ICSME, MSR, ICPC, SANER, SCAM, and others. He is a member of IEEE Computer Society and ACM.