We welcome you to the 4th ACM Recommender Systems Conference (ACM RecSys 2010), this time from beautiful and sunny Barcelona. After three fantastic preceding conferences, we took on the challenge of continuing on the success trend knowing that a city such as Barcelona would offer the ideal setting. Not only is Barcelona a top tourism destination but it has also a very bustling industry that includes large companies and young startups in recommender systems and related areas.
RecSys is maturing as a research area and you will find several signs of that maturity reflected in these proceedings. One sign is becoming cumulative: performance of new algorithms is compared to previous algorithms and contrasts are made between performance on different datasets. With maturity, however, also comes a questioning of assumptions. For example, you will find papers that argue for different measures of success than prediction accuracy, such as stability and coverage.
Despite maturity, the field also continues to be creative. You will find papers exploring new ways of collecting user preferences beyond like/dislike of individual items, such as pairwise orderings or allocation of points among a set of items. You will also find research identifying and exploiting the specific characteristics of non-standard item types to recommend, ranging from people to groups to recipes to research papers.
For the first time, ACM RecSys 2010 had more than 200 submissions. Of 129 full paper submissions, 25 were accepted (19.4%) for oral presentation at the conference. Of 78 short paper submissions, 32 were accepted (41.0%) for poster presentation. In addition, we introduced a new track for submission of demos and case study reports, which will also be presented at the poster session.
The program also includes three invited tutorials, by senior researchers Joe Konstan, Ricardo Baeza-Yates, and Guy Shani, and an invited keynote by Edouard Servan-Schreiber. The conference begins with an industry panel examining the future of recommender systems in several different industries, and how it relates to search. Panelists from Neo Metrics Barcelona, Bloomberg.com, YouTube, SAP, and Avail Intelligence will join industry chairs Ido Guy and Alex Jaimes on stage. Tuesday morning begins with a panel on contests and challenges. In addition to a skeptic's voice questioning the wisdom of contests overall, the panel will explore alternative tasks for contests besides prediction and ranking, such as making creative use of the outputs of a fixed recommender engine, or eliciting inputs for a recommender engine.
In addition to the main program, we would also like to highlight the growing success of the collocated workshops. This year we have seven workshops distributed on two different days of the conference. These workshops include most of the new trending research lines in recommender systems. They focus on application areas of RecSys such as music, e-Learning, or the social web. Others analyze some cross-cutting concerns in research such as how to deal with contextual or heterogeneous information, or how to bring the user into the loop in the evaluation phase. Finally, one workshop specifically focuses on the practical concerns of deploying and evaluating recommender systems in real-world settings.