Yahoo at KDD and SIGMOD

NEWS
Jul 7, 2009

It was an exciting week as two major conferences took place concurrently during the week of June 28. The 15th ACM SGKDD Conference on Knowledge Discovery and Data Mining took place in Paris, while the annual ACM SIGMOD/PODS Conference found its base in Providence. Yahoo walked away the winner of the Best Paper Award at both conferences, in addition to earning a high number of accepted papers. At KDD, Yahoo earned 12 out of 142 total accepted papers and Yehuda Koren’s “Collaborative Filtering with Temporal Dynamics” won Best Paper. Work presented at KDD alluded to the fact that a major focus of Web-related data mining research will be the individual user. In the past, the focus was on problems of efficiently retrieving and presenting information that is relevant for most users collectively. Now research is heading in the direction of optimizing algorithms for individual users by learning and observing the actions of these users. This is evident in the work presented by Yahoo Labs, with papers such as “Large Scale Behavioral Targeting,” “Mining Broad Latent Query Aspects from Search Sessions,” “Modeling the Dynamics of Individual Human Communication,” “Modeling and Predicting User Behavior in Sponsored Search,” and “A Case Study of Behavior-driven Conjoint Analysis on Yahoo Front Page Today Module.” SIGMOD/PODS proved to be just as successful for Yahoo, winning three awards this year including the Best Paper Award for "Generating Example Data for Dataflow Programs" by Chris Olston, Shubham Chopra and Utkarsh Srivastava. Bee-Chung Chen and Ashwin Machanavajjhala also earned Best Dissertation Runner-Up Awards for their work on “Cube-Space Data Mining” and "Defining and Enforcing Privacy in Data Sharing”, respectively. The conference opened with a keynote by Hasso Plattner, cofounder of software giant SAP. The main takeaway of his presentation and major theme of the conference was that column stores and multi-core computation have improved the efficiency of databases by at least two orders of magnitude, opening a new world of possibilities in information access.