Keynote Speaker and Panelists confirmed

We are happy to announce that the keynote speaker and panelists for the BARS workshop have been confirmed.

Torben Brodt from plista GmbH will give a keynote on “The Search for the Best Live Recommender System”. plista is a data-driven content- and ad distribution network, mainly active in the German speaking world. Its technology is used on thousands of premium websites for recommending millions of news articles and ads to even more users. Currently, over 5,000 requests are processed per second. In his talk, he will present challenges and opportunities that arise from handling such vast amounts of data in real-time. In particular, he will illustrate why users’ context (e.g., category, geo-location, day of the week) plays a key role in the provision of successful recommender algorithms and will outline the importance of a thorough evaluation of our techniques. Besides, he will talk about their experience in organizing a real-time news recommender contest which provides researchers the chance to run their algorithms in our production system, thus benefiting from real feedback from real users.

The workshop will end with a panel session where experts from Academia and Industry who will discuss emerging challenges in the field. Panel members are Paul N. Bennett (Microsoft Research), Jeremy Pickens (Catalyst Repository Systems), Jimmy Lin (University of Maryland) and Neil Hurley (UCD). We are looking forward to some lively discussions.

CFP: Benchmarking Recommender Systems

This is a call for papers for the ACM TIST special issue on Benchmarking Recommender Systems.

Call for Papers
ACM Transactions on Intelligent Systems and Technology
Special Issue on Recommender System Benchmarking

Overview

Recommender systems add value to vast content resources by matching users with items of interest. In recent years, immense progress has been made in recommendation techniques. The evaluation of these systems is still based on traditional information retrieval and statistics metrics, e.g. precision, recall, RMSE often not taking the use-case and situation of the system into consideration.
However, the rapid evolution of recommender systems in both their goals and their application domains foster the need for new evaluation methodologies and environments.

Continue reading CFP: Benchmarking Recommender Systems

Accepted

We are pleased to announce that the Workshop on Benchmarking Adaptive Retrieval and Recommender Systems has been accepted to ACM SIGIR in Dublin, Ireland.

This website will be continuously updated with information regarding the workshop.

In conjunction with ACM SIGIR. Dublin, August 1, 2013.

Get Adobe Flash player