Probabilistic Graphical Models in Microsoft's Online Services: TrueSkill, AdPredictor, and Matchbox

Add to your list(s) Download to your calendar using vCal

• Thore Graepel, MSR Cambridge
• Wednesday 12 October 2011, 14:15-15:15
• Lecture Theatre 1, Computer Laboratory.

If you have a question about this talk, please contact Stephen Clark.

Abstract: Probabilistic Graphical Models play a crucial role in Microsoft’s online services. In this talk, I will describe three powerful applications of graphical model inference in practice. 1. TrueSkill is Xbox Live’s Ranking and Matchmaking system and ensures that gamers online have balanced and exciting matches with equally skilled opponents. 2. AdPredictor is the system that estimates click-through rates (CTR) for ad selection and pricing within Microsoft’s search engine Bing. 3. Matchbox is a large scale Bayesian recommender system that combines aspects of collaborative filtering and content-based recommendation. It is currently being used for tweet recommendation within projectemporia.com. All three systems have in common that they are based on factor graph models and approximate Bayesian inference. They operate at a very large scale involving millions of gamers, billions of ad impressions, and millions of tweets, respectively. I will discuss the underlying graphical models and inference algorithms as well as application-specific insights and findings. Time permitting, I will show the three systems in action. This is based on joint work with Ralf Herbrich, David Stern, Thomas Borchert, Tom Minka, and Joaquin Quiñonero Candela.

This talk is part of the Wednesday Seminars - Department of Computer Science and Technology series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge talks
• Chris Davis' list
• Department of Computer Science and Technology talks and seminars
• Graduate-Seminars
• Guy Emerson's list
• Interested Talks
• Lecture Theatre 1, Computer Laboratory
• School of Technology
• Trust & Technology Initiative - interesting events
• Wednesday Seminars - Department of Computer Science and Technology
• bld31
• computer science
• se393's list

Note that ex-directory lists are not shown.