Get on with it! Recommender system industry challenges move towards real-world, online evaluation

Recommender systems have enormous commercial importance in connecting people with content, information, and services. Historically, the recommender systems community has benefitted from industry-academic collaborations and the ability of industry challenges to drive forward the state of the art. However, today’s challenges look very different from the NetFlix Prize in 2009. This talk features speakers representing two ongoing recommendation challenges that typify the direction in which such challenges are rapidly evolving. The first is the ACM RecSys Challenge (http://2016.recsyschallenge.com), which addresses the task of recommending job openings. Behind this challenge is XING, the social network for business contacts that serves 10 million users in the German-speaking market. The second is CLEF NewsREEL (http://www.clef-newsreel.org/), which addresses the task of recommending news items in online portals. Behind this challenge is plista, specialists in data-driven native advertising and content distribution. Taken together these examples represent the movement of recommender system industry towards offering challenges involving real-world, online evaluation. Success in such challenges requires algorithm s capable of integrating the multiple sources of information available in real-world scenarios. Further, the algorithms must be effective from the perspective of user satisfaction, but also be able to meet technical constraints (i.e., response time, system availability) and business requirements (i.e., item coverage).

 

Andreas Lommatzsch, DAI-Lab, Berlin Institute of Technology, Berlin, Germany

Andreas received his PhD degree in Computer Science from the TU Berlin. His research focuses on distributed knowledge management and information retrieval and systems. Since 2009 he has been a senior researcher and project coordinator in the domain of Recommender Systems and Machine Learning. His primary interests lie in the areas of recommendations based on data-streams and context-aware meta-recommender algorithms. He is one of the organizers of the CLEF NewsREEL challenge focusing on recommender algorithms for online news portals.

 

Jonas Seiler, plista, Berlin, Germany

Jonas leads the Machine Learning Team at plista. Together with his team, he is responsible for a recommendation system delivering millions of Ad- and News Article Recommendations per day. He received his MSc in Computational Neuroscience at the Bernstein Center For Computational Neuroscience Berlin and specialized in Ensemble Learning in Recommendation System. The CLEF NewsREEL challenge addresses the challenge of online recommendation at plista.

 

Daniel Kohlsdorf, XING, Hamburg, Germany

Daniel is a Data Scientist at XING with a focus on data mining projects and recommender systems. His research interests include automated behavior analysis of humans and dolphins, contextual computing and data mining with the application to recommender systems. At XING, he is developing large-scale recommender systems that serve millions of users and handle hundreds of requests per second. He received his PhD in computer science from Georgia Tech with a specialization in machine learning and computational perception and a masters degree in informatics from University Bremen. He is an organizer of the RecSys Challenge at ACM RecSys 2016 on job recommendation.