Recommender Systems (as-a-Service) for Academia: The Pain and Gain in Building, Operating, and Researching them
Joeran Beel, SCSS, TCD
12-1pm 24th Nov 2017
Research on recommender systems is a challenging task, as is building and operating such systems. Major challenges include non-reproducible research results, dealing with noisy data, and answering many questions such as how many recommendations to display, where, and how often, and, of course, how to generate recommendations most effectively. In the past six years, we built three research-article recommender systems for digital libraries and reference managers and conducted research on these systems. In this talk, I share the experiences that we made during that time, provide a summary of our research results, and an outlook to upcoming challenges. Among others, I discuss the required skills to build recommender systems, and why the literature provides little help in identifying promising recommendation approaches. I explain the challenge in creating a randomization engine to run A/B tests, and why several of our experiments delivered disappointing and non-reproducible results. The talk concludes with a discussion of the need and potential for self-learning recommender systems to overcome the problem of unreproducible research.
Joeran Beel is Assistant Professor in Intelligent Systems at Trinity College Dublin and a member of the ADAPT Centre since December 2016. His research focuses on recommender systems (recommendations as-a-service and recommender-system evaluation) and related technologies such as machine learning and natural language processing. Joeran has published three books and over 50 peer-reviewed articles and has been awarded various grants for research projects, patent applications, and prototype development as well as some business start-up funding. Joeran studied and researched in the USA (Berkeley), Australia (Sydney), Germany (Magdeburg & Konstanz), Cyprus (Nicosia) and the UK (Lancaster). He has an M.Sc. in Project Management, an M.Sc. in Business Information Systems and a PhD in Computer Science. Prior to Trinity College, Joeran worked as IT product manager in the tourism industry (Munich, Germany), and as a postdoctoral researcher at the National Institute of Informatics (NII) in Tokyo, Japan.