On How Machine Learning and Auction Theory Power Facebook Advertising

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=94s0yYECeR8


Duration: 54:21
19,241 views
279

Eric Sodomka, Facebook
Algorithmic Game Theory and Practice
https://simons.berkeley.edu/talks/eric-sodomka-2015-11-17



Other Videos By Simons Institute for the Theory of Computing


2015-12-08From the Inside: Fine-Grained Complexity and Algorithm Design
2015-12-08From the Inside: Economics and Computation
2015-11-20Bitcoin's Incentive Structure
2015-11-20Dynamic Pricing in Ride-Sharing Platforms
2015-11-20AGT and Machine Learning
2015-11-20Business Model Analysis
2015-11-20The Limits of Reputation in Platform Markets
2015-11-20Outsourcing Tasks Online: Matching Supply and Demand on Peer-to-Peer Internet
2015-11-20Kidney Exchange: Algorithms and Incentives
2015-11-20Designing Online Advertising Markets
2015-11-20On How Machine Learning and Auction Theory Power Facebook Advertising
2015-11-20Strong Truthfulness in Multi-signal Peer Prediction with Overlapping Tasks
2015-11-20The State of Techniques for Solving Large Imperfect-Information Games
2015-11-20An Evolutionary Model of Economic Behavior, Bounded Rationality, and Intelligence
2015-11-20The Design of Financial Exchanges: Some Open Questions at the Intersection of Econ and CS
2015-11-20Robust Inference for Games via Theoretical Guarantees
2015-11-20Security Games: Key Algorithmic Principles, Deployed Applications and Research Challenges(*)
2015-11-20Algorithmic Trading and Machine Learning
2015-11-20Informational Substitutes and Complements for Prediction
2015-11-20Incentive Auctions and Spectrum Repacking
2015-11-13Research Challenges in Designing the US Incentive Auction


Tags:
Simons Institute
UC Berkeley
computer science
theory of computing
Economics and Computation
Eric Sodomka