Recommender System research has evolved to focus on developing algorithms capable of high performance in online systems. This development calls for a new evaluation infrastructure that supports multi-dimensional evaluation of recommender systems. Today’s researchers should analyze algorithms with respect to a variety of aspects including predictive performance and scalability. Researchers need to subject algorithms to realistic conditions in online A/B tests. We introduce two resources supporting such evaluation methodologies: the new data set of stream recommendation interactions released for CLEF NewsREEL 2017, and the new Open Recommendation Platform (ORP). The data set allows researchers to study a stream recommendation problem closely by “replaying” it locally, and ORP makes it possible to take this evaluation “live” in a living lab scenario. Specifically, ORP allows researchers to deploy their algorithms in a live stream to carry out A/B tests. To our knowledge, NewsREEL is the first online news recommender system resource to be put at the disposal of the research community. In order to encourage others to develop comparable resources for a wide range of domains, we present a list of practical lessons learned in the development of the dataset and ORP.@en

News recommender systems provide users with access to news stories that they find interesting and relevant. As other online, stream-based recommender systems, they face particular challenges, including limited information on users’ preferences and also rapidly fluctuating item collections. In addition, technical aspects, such as response time and scalability, must be considered. Both algorithmic and technical considerations shape working requirements for real-world recommender systems in businesses. NewsREEL represents a unique opportunity to evaluate recommendation algorithms and for students to experience realistic conditions and to enlarge their skill sets. The NewsREEL Challenge requires participants to conduct data-driven experiments in NewsREEL Replay as well as deploy their best models into NewsREEL Live’s ‘living lab’. This paper presents NewsREEL 2017 and also provides insights into the effectiveness of NewsREEL to support the goals of instructors teaching recommender systems to students. We discuss the experiences of NewsREEL participants as well as those of instructors teaching recommender systems to students, and in this way, we showcase NewsREEL’s ability to support the education of future data scientists. @en

The CLEF NewsREEL challenge allows researchers to evaluate news recommendation algorithms both online (NewsREEL Live) and offline (News-REEL Replay). Compared with the previous year NewsREEL challenged participants with a higher volume of messages and new news portals. In the 2017 edition of the CLEF NewsREEL challenge a wide variety of new approaches have been implemented ranging from the use of existing machine learning frameworks, to ensemble methods to the use of deep neural networks. This paper gives an overview over the implemented approaches and discusses the evaluation results. In addition, the main results of Living Lab and the Replay task are explaine@en

Successful news recommendation requires facing the challenges of dynamic item sets, contextual item relevance, and of fulfilling non-functional requirements, such as response time. The CLEF NewsREEL challenge is a campaign-style evaluation lab allowing participants to tackle news recommendation and to optimize and evaluate their recommender algorithms both online and offline. In this paper, we summarize the objectives and challenges of NewsREEL 2016. We cover two contrasting perspectives on the challenge: that of the operator (the business providing recommendations) and that of the challenge participant (the researchers developing recommender algorithms). In the intersection of these perspectives, new insights can be gained on how to effectively evaluate real-time stream recommendation algorithms.@en

The CLEF NewsREEL challenge is a campaign-style evaluation lab allowing participants to evaluate and optimize news recommender algorithms. The goal is to create an algorithm that is able to generate news items that users would click, respecting a strict time constraint. The lab challenges participants to compete in either a “living lab” (Task 1) or perform an evaluation that replays recorded streams (Task 2). In this report, we discuss the objectives and challenges of the NewsREEL lab, summarize last year’s campaign and outline the main research challenges that can be addressed by participating in NewsREEL 2016. @en