Seminar: Applications of Recommender Systems and Machine Learning in Software Engineering

The proliferation of disruptive Machine Learning (ML) and especially Deep Learning (DL) algorithms has enabled a plethora of applications across several domains. Such techniques work on the basis of complex artificial neural networks, which are capable of effectively learning from data by means of a large number of parameters distributed in different network layers. In this way, ML/DL techniques are an advanced paradigm that brings in substantial improvement in performance compared to conventional learning algorithms. We have successfully studied and deployed various Machine Learning techniques in Software Engineering and other domains.

In online shopping platforms, recommender systems are considered to be an indispensable component, allowing business owners to offer personalized products to customers. The development of such systems has culminated in well-defined recommendation algorithms, which in turn prove their usefulness in other fields, such as the entertainment industry, or employment-oriented service. Recommender systems in software engineering have been conceptualized on a comparable basis, i.e., they assist developers in navigating large information spaces and getting instant recommendations that are helpful to solve a particular development task. In this sense, they provide developers with useful recommendations, which may consist of different items, such as code examples, topics, third-party components, documentation, to name a few.

The main topics presented in the seminar are as follows:

• Notable applications of ML/DL, and recommender systems in Software Engineering.
• Adversarial machine learning.
• Ongoing research issues (Mining Stack Overflow, API evolution, API migration, technical debt).