Recommender Systems and the New New Economics of Information
by George Loewenstein (Carnegie Mellon University, USA)
George Stigler pioneered the economics of information in the 1960s with his observation that information is a scarce and valuable commodity. Stigler assumed people value information to the extent, and only to the extent, that it helps them to make better decisions, and that people update their beliefs rationally, in response to new information. Stigler won the Nobel prize for his contibution, as did three economists, George Akerlof, Michael Spence and Joseph Stiglitz ten years later. This second wave of research, that came to be called the “new economics of information” adhered to Stigler’s assumptions, but examined consequences of asymmetric information – i.e., the fact that interacting individuals often possess different information sets. In this talk I will discuss my research on four phenomena that are key to the information age that don’t fit neatly into either wave of economic research on information: curiosity (the desire for information for its own sake), privacy (the desire to withhold information), information avoidance, and the desire to share information. The last of these topics is most relevant to recommender systems, so I will devote special attention to it.
About the Speaker
George Loewenstein is the Herbert A. Simon University Professor of Economics and Psychology at Carnegie Mellon University. He received his PhD in economics from Yale University in 1985 and since then has held academic positions at The University of Chicago and Carnegie Mellon University, and fellowships at Center for Advanced Study in the Behavioral Sciences, The Institute for Advanced Study in Princeton, The Russell Sage Foundation, The Institute for Advanced Study (Wissenschaftskolleg) in Berlin, and the London School of Economics. His research focuses on applications of psychology to economics, and his specific interests include decision making over time, bargaining and negotiations, psychology and health, privacy, curiosity, information avoidance, law and economics, the psychology of adaptation, the role of emotion in decision making, the psychology of curiosity, conflict of interest, and “out of control” behaviors such as impulsive violent crime and drug addiction. He is one of the founders of the fields of behavioral economics and neuroeconomics.
Improving Higher Education—Learning Analytics & Recommender Systems Research
by George Karypis (University of Minnesota, USA)
An enduring issue in higher education is student retention to successful graduation. Studies in the U.S. report that average six-year graduation rates across higher-education institutions is 59% and have remained relatively stable over the last 15 years. For those that do complete a college degree, less than half complete within four-years. Requiring additional terms or leaving college without receiving a bachelor’s degree has high human and monetary costs and deprives students from the economic benefits of a college credential (over $1 million in a lifetime and even higher in STEM fields). Moreover, when students do not succeed in graduating, local and national communities struggle to create an educated workforce. Estimates indicate that by 2020 over 64% of the jobs in the U.S. will require at least some post-secondary education. These challenges have been recognized by the U.S. National Research Council, which identified that there is a critical need to develop innovative approaches to enable higher-education institutions retain students, ensure their timely graduation, and are well-trained and workforce ready in their field of study. Failure to do so represents a significant problem as it deprives the U.S. of the highly skilled workforce that it needs to successfully compete in the modern world.
This talk describes various efforts under way to develop “Big Data” methods to analyze in a comprehensive manner, the large and diverse types of education and learning-related data in order to improve undergraduate education. These methods are motivated by and are designed to address various interrelated issues that have a significant impact on college student success and include: (i) academic pathways towards successful and timely graduation from the student perspective; (ii) effective pedagogy by instructors; and (iii) retention and persistence of students from the institutional and advisor perspective. In addition, the talk will discuss areas in which research methods and approaches originally developed by the recommender systems community can be applied to this domain.
About the Speaker
George Karypis is a Distinguished McKnight University Professor and an ADC Chair of Digital Technology at the Department of Computer Science & Engineering at the University of Minnesota, Twin Cities. His research interests span the areas of high performance computing, data mining, recommender systems, information retrieval, bio-informatics, cheminformatics, and scientific computing. His research has resulted in the development of software libraries for serial and parallel graph partitioning (METIS and ParMETIS), hypergraph partitioning (hMETIS), for parallel Cholesky factorization (PSPASES), for collaborative filtering-based recommendation algorithms (SUGGEST), clustering high dimensional datasets (CLUTO), finding frequent patterns in diverse datasets (PAFI), and for protein secondary structure prediction (YASSPP). He has coauthored over 270 papers on these topics and two books (“Introduction to Protein Structure Prediction: Methods and Algorithms” (Wiley, 2010) and “Introduction to Parallel Computing” (Addison Wesley, 2003, 2nd edition)). He is on the editorial boards of many journals and in the program committees of many conferences and workshops on these topics.
Personalization is a Two-Way Street
by Ronny Lempel (Outbrain, Israel)
Recommender systems are first and foremost about matching users with items the systems believe will delight them. The “main street” of personalization is thus about modeling users and items, and matching per user the items predicted to best satisfy the user. This holds for both collaborative filtering and content-based methods. In content discovery engines, difficulties arise from the fact that the content users natively consume on publisher sites does not necessarily match the sponsored content that drives the monetization and sustains those engines. The first part of this talk addresses this gap by sharing lessons learned and by discussing how the gap may be bridged at scale with proper techniques.
The second part of the talk focuses on personalization of audiences on behalf of content marketing campaigns. From the marketers’ side, optimizing audiences was traditionally done by refining targeting criteria, basically limiting the set of users to be exposed to their campaigns. Marketers then began sharing conversion data with systems, and the systems began optimizing campaign conversions by serving the campaign to users likely to transact with the marketer. Today, a hybrid approach of lookalike modeling combines marketers’ targeting criteria with recommendation systems’ models to personalize audiences for campaigns, with marketer ROI as the target.
About the Speaker
Ronny Lempel joined Outbrain in May 2014 as VP of Outbrain’s Recommendations Group, where he oversees the computation, delivery and auction mechanisms of the company’s recommendations. Prior to joining Outbrain, Ronny spent 6.5 years as a Senior Director at Yahoo Labs. Ronny joined Yahoo in October 2007 to open and establish its Research Lab in Haifa, Israel. During his tenure at Yahoo, Ronny led R&D activities in diverse areas, including Web Search, Web Page Optimization, Recommender Systems and Ad Targeting. In January 2013 Ronny was appointed Yahoo Labs’ Chief Data Scientist in addition to his managerial duties.
Prior to joining Yahoo, Ronny spent 4.5 years at IBM Research, where his duties included research and development in the area of enterprise search systems. During his tenure at IBM, Ronny managed the Information Retrieval Group at IBM’s Haifa Research Lab for two years.
Ronny received his PhD, which focused on search engine technology, from the Faculty of Computer Science at Technion, Israel Institute of Technology in early 2003. Ronny has authored over 40 research papers in leading conferences and journals, and holds 18 granted US patents. He regularly serves on program and organization committees of Web-focused conferences, and has taught advanced courses on Search Engine Technologies and Big Data Technologies at Technion.
Memory Networks for Recommendation
by Jason Weston (Facebook, USA)
Memory networks are a recently introduced model that combines reasoning, attention and memory for solving tasks in the areas of language understanding and dialog — where one exciting direction is the use of these models for dialog-based recommendation. In this talk we describe these models and how they can learn to discuss, answer questions about, and recommend sets of items to a user. The ultimate goal of this research is to produce a full dialog-based recommendation assistant. We will discuss recent datasets and evaluation tasks that have been built to assess these models abilities to see how far we have come.
About the Speaker
Jason Weston is a research scientist at Facebook, NY, since Feb 2014. He earned his PhD in machine learning at Royal Holloway, University of London and at AT&T Research in Red Bank, NJ (advisors: Alex Gammerman, Volodya Vovk and Vladimir Vapnik) in 2000. From 2000 to 2001, he was a researcher at Biowulf technologies. From 2002 to 2003 he was a research scientist at the Max Planck Institute for Biological Cybernetics, Tuebingen, Germany. From 2003 to 2009 he was a research staff member at NEC Labs America, Princeton. From 2009 to 2014 he was a research scientist at Google, NY. His interests lie in statistical machine learning and its application to text, audio and images. Jason has published over 100 papers, including best paper awards at ICML and ECML. He was part of the YouTube team that won a National Academy of Television Arts & Sciences Emmy Award for Technology and Engineering for Personalized Recommendation Engines for Video Discovery. He was listed as the 16th most influential machine learning scholar at AMiner and one of the top 50 authors in Computer Science in Science.
