A New Understanding of Prediction Markets Via No-Regret Learning

Details A New Understanding of Prediction Markets Via No-Regret Learning A New Understanding of Prediction Markets Via No-Regret Learning

2010-02-26

arxiv.org/abs/1003.0034v1

Computer Science

Artificial Intelligence

Scientific paper

We explore the striking mathematical connections that exist between market scoring rules, cost function based prediction markets, and no-regret learning. We show that any cost function based prediction market can be interpreted as an algorithm for the commonly studied problem of learning from expert advice by equating trades made in the market with losses observed by the learning algorithm. If the loss of the market organizer is bounded, this bound can be used to derive an O(sqrt(T)) regret bound for the corresponding learning algorithm. We then show that the class of markets with convex cost functions exactly corresponds to the class of Follow the Regularized Leader learning algorithms, with the choice of a cost function in the market corresponding to the choice of a regularizer in the learning problem. Finally, we show an equivalence between market scoring rules and prediction markets with convex cost functions. This implies that market scoring rules can also be interpreted naturally as Follow the Regularized Leader algorithms, and may be of independent interest. These connections provide new insight into how it is that commonly studied markets, such as the Logarithmic Market Scoring Rule, can aggregate opinions into accurate estimates of the likelihood of future events.

Affiliated with

Also associated with

No associations

Rating

A New Understanding of Prediction Markets Via No-Regret Learning does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with A New Understanding of Prediction Markets Via No-Regret Learning, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A New Understanding of Prediction Markets Via No-Regret Learning will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-628980