Important Research Challenges in Recommenders
by John Riedl (University of Minnesota), John Sanders (Netflix) and Todd Beaupre (Yahoo!)
John Riedl will host a panel of successful recommender systems practitioners from industry, who will share their perspectives on the most important open research challenges. They will focus on research challenges that have greatest impact on recommender systems in practice, but that need the sort of break-through solutions that are best achieved in the research lab. The panelists will have detailed prepared remarks, and there will be time for discussion with members from the audience.
Bayesian Modeling for Recommender Systems
by Asim Ansari (Columbia University)
Bayesian methods are popular in marketing and in machine learning for targeting and personalization activities. Bayesian models yield parameter estimates for each user and allow the sequential integration of information, both of which are crucial for making effective recommendations In this tutorial we will cover how Bayesian models have been used in recommender systems research. We will concentrate on approaches developed within the field of marketing and highlight how Bayesian modeling and MCMC computation can be used in tandem for making personalized recommendations. We will also highlight the challenges involved in computation and scalability.
Using Social Trust for Recommender Systems
by Jennifer Golbeck (University of Maryland)
As the Web has shifted to an interactive environment where vast amounts of content is created by users, the question of whom to trust and what information to trust has become both more important and more difficult to answer. At the same time, social networks have become very popular with over a billion accounts shared across hundreds of networks. Social trust relationships, derived from social networks, are uniquely suited to speak to the quality of online information; recommender systems are designed to personalize, sort, aggregate, and highlight information. Merging social networks, trust, and recommender systems can improve the accuracy of recommendations and improve the user’s experience. In this tutorial, we will cover the use of social trust in recommender systems. Topics including the computation of trust in social networks, integration of trust into recommender systems, and a discussion of when trust offers benefits and the challenges it presents.
