DO&IT Seminar Series http://www.rhsmith.umd.edu/doit/events/seminars.aspx Speaker: Dr. Claudia Perlich, Dstillery Date: Friday, February 7, 2014 Time: 1:15 pm - 2:30 pm Location: Room 1518 Title: "Large Scale Automated Machine Learning for Digital Advertising: Challenges and Opportunities" Abstract: Display advertising is maybe one of the most exciting playgrounds for applied research in data analytics, machine learning, and predictive modeling. At Dstillery we observe daily about 10 Billion user events representing the digital and geo-physical journeys of millions of people on desktops, tablets and mobile phones. Our core analytical focus is finding good prospective customers for marketers and serving them ads while preserving their privacy. In particular, we do not tag browsers with any behavioral labels but instead work only with the set of hashed URL’s that the browser has visited. This can be social media, user generated content, or Internet sites in general. A second core component is bid optimization. Billions of online display advertising spots are purchased on a daily basis through real time bidding exchanges (RTBs). Advertising companies bid for these spots on behalf of a company or brand in order to purchase these spots to display banner advertisements. These bidding decisions must be made in fractions of a second based on what location (Internet site) has a spot available and who would see the advertisement. This talk will touch on a number of challenges and analytical approaches to privacy preserving representations, robust high-dimensional modeling, large-scale automated learning system, causal estimation from observational data, transfer learning, and fraud detection. Bio: Claudia Perlich acts currently as Chief Scientist at Dsillery (previously m6d) and in this role designs, develops, analyzes and optimizes the machine learning that drives digital advertising. She has published over 50 scientific articles, and holds multiple patents in machine learning. She has won many data mining competitions and best paper awards at KDD and is acting as General Chair for KDD 2014. Prior to joining m6d in February 2010, Claudia worked in the Predictive Modeling Group at IBM’s Watson Research Center, concentrating on data analytics and machine learning for complex real-world domains and applications. Claudia holds a PhD in Information Systems from NYU and continues to teach as an Adjunct Professor in the NYU Stern MBA program. Van Munching Hall ▫ Room 4306 ▫ Telephone 301-405-8654 College Park, MD ▫ University of Maryland