Skip to main content
Browse by:
GROUP

Combinatorial Prediction Markets and Connections to Online Learning

Event Image
Wednesday, October 08, 2014
3:30 pm - 4:30 pm
Jenn Wortman Vaughan, Microsoft Research
Machine Learning Seminar

12noon lunch and lecture ¿Perspectives in Machine Learning¿3:30-4:30pm Seminar reception followingA prediction market is a financial market designed to aggregateinformation. In a typical prediction market, participants tradesecurities with payoffs linked to the outcome of a future event, suchas a security that will be worth $1 if a Democrat wins the 2016 USPresidential election and $0 otherwise. An expectation maximizingtrader who believes that the probability of a Democrat winning is pshould be willing to purchase this security at any price below $p,or sell it at any price above $p, and the current market price canbe viewed as the traders' collective estimate of how likely it isthat a Democrat will win the election.Jenn Wortman Vaughan is a Researcher at Microsoft Research, New YorkCity, where she studies algorithmic economics, market design, machinelearning, and social computing, using techniques from theoretical computerscience, optimization, and probability theory. Contact: Katherine Heller kheller@gmail.com for more information or to meet with Jenn

Type: LECTURE/TALK
Contact: Sayan Mukherjee