The Recommender Problem Revisited
by Xavier Amatriain (Netflix Inc., USA)
In 2006, Netflix announced a $1M prize competition to advance recommendation algorithms. The recommendation problem was simplified as the accuracy in predicting a user rating measured by the Root Mean Squared Error. While that formulation helped get the attention of the research community in the area, it may have put an excessive focus on what is simply one of possible approaches to recommendations. In this tutorial we will describe different components of modern recommender systems such as: personalized ranking, similarity, explanations, context-awareness, or search as recommendation. We will use the Netflix use case as a driving example of a prototypical industrial-scale recommender system. We will also review the usage of modern algorithmic approaches that include algorithms such as Factorization Machines, Restricted Boltzmann Machines, SimRank, Deep Neural Networks, or Listwise Learning-to-rank.
Date
Oct 6, 2014
Location
Alexandria Room
Slides
Link to SlideShare (external)
Personalized Location Recommendation on Location-based Social Networks
by Huiji Gao, Jiliang Tang, and Huan Liu (Arizona State University, USA)
Personalized location recommendation is a special topic of recommendation, as it is related to human mobile behavior in the real world regarding various contexts including spatial, temporal, social, and content. The development of this topic is subject to the availability of human mobile data. The recent rapid growth of location-based social networks has alleviated such limitation, which promotes the development of various location recommendation techniques. Given these techniques focusing on different facets of location-based social networking data, it is the time for researchers to be informed of new development of location-based social networking services and related recommendation techniques, and enable novel applications over the vast amounts of valuable data on location-based social networks.
This tutorial offers an overview, in a data mining perspective, of personalized location recommendation on location-based social networks. It introduces basic concepts, summarizes unique LBSN characteristics and research opportunities, elaborates associated challenges, reviews state-of-the-art algorithms with illustrative examples and real-world LBSN dataset, and discusses effective evaluation methods. The tutorial is suitable for academic and industrial researchers, graduate students, and practitioners who want to learn the details of the personalized location recommendation techniques w.r.t. spatial, temporal, social, and content aspects of location-based social network data.
For more information, please visit the tutorial homepage (external link).
Date
Oct 6, 2014
Location
Alexandria Room
Cross-Domain Recommender Systems
by Ivan Cantador (Universidad Autónoma de Madrid, Spain) and Paolo Cremonesi (Politecnico di Milano, Italy)
The proliferation of e-commerce sites and online social networks has led users to provide feedback and maintain profiles in multiple systems, reflecting a variety of their tastes and interests. Leveraging all the user preferences available in several systems or domains may be beneficial for generating more encompassing user models and better recommendations, e.g. through mitigating the cold-start and sparsity problems in a target domain, or enabling cross-selling recommendations for items from multiple domains. Cross-domain recommender systems, thus, aim to generate or enhance personalized recommendations in a target domain by exploiting knowledge (mainly user preferences) from source domains. In this tutorial, we formalize the cross-domain recommendation problem, unify the perspectives it has been addressed in distinct disciplines – user modeling, recommender systems, and machine learning -, analytically categorize, describe and compare prior work, and identify open issues for future research.
Outline
- Introduction
- Formulation of the cross-domain recommendation problem
- Notions of domain
- Cross-domain recommendation tasks
- Cross-domain recommendation scenarios
- Categorization of cross-domain recommendation techniques
- Aggregating knowledge
- Linking and transferring knowledge
- Evaluation of cross-domain recommender systems
- Cross-domain recommendation goals
- Evaluation methodologies and metrics
- Datasets
- Open research issues
The tutorial assumes familiarity with recommender systems. Some background
in data mining and machine learning may be helpful, but is not required.
Date
Oct 6, 2014
Location
Alexandria Room
Slides
recsys2014-tutorial-cross_domain
Social Recommender Systems
by Ido Guy (Yahoo! Labs) and Werner Geyer (IBM Research)
In recent years, with the proliferation of the social web, users are increasingly exposed to social overload and the designers of social web sites are challenged to attract and retain their user basis. Social recommender systems are becoming an integral part of virtually any leading website, playing a key factor in its success: First, they aim to address the overload problem by helping users to find relevant content. Second, they can provide recommendations for content creation, increasing participation and user retention. In this tutorial, we will review the broad domain of social recommender systems, their application for the social web, the underlying techniques and methodologies; the data in use, recommended entities, and target population; evaluation techniques; and open issues and challenges.
Date
Oct 6, 2014
Location
Alexandria Room
