PM Atlas PM Atlas home

Concept · mechanism-design

Peer Prediction

Methods for eliciting honest subjective reports by comparing respondents against each other statistically. When there is no ground truth to score against, peer-prediction mechanisms use the correlation structure between reporters to incentivize truth-telling.

Key insights

In their words

Peer prediction systems operate by evaluating each agent's prediction not against an objective reality but against the other agents' predictions. Remarkably, under certain conditions such systems can induce truth telling in equilibrium.· Chen & Pennock, *Designing Markets for Prediction*
We present a novel incentive-compatible prediction market mechanism to elicit and efficiently aggregate information from a pool of agents without observing the outcome, by paying agents the negative cross-entropy between their prediction and that of a carefully chosen reference agent.· Srinivasan, Karger & Chen, *Self-Resolving Prediction Markets for Unverifiable Outcomes*
A reference agent with access to more information can serve as a reasonable proxy for the ground truth.· SKC, *ibid.*
Markets resolve using crowd consensus as the outcome, with delta-based scoring rewarding participants for moving markets toward final consensus.· michaellwy, *Explainer on Self-Resolving Prediction Markets*

Where it matters

Peer prediction is the only mechanism class that lets prediction markets cover questions without ground truth · opinion markets, taste markets, subjective forecasts, "is this true?" markets about contested information. Polymarket and Kalshi avoid these entirely (they require verifiable resolution); the next wave of prediction-market design (self-resolving markets, on-chain truth markets) is being built on peer-prediction foundations. The SKC mechanism is the most likely on-chain instantiation.

Connections

Platforms linked to this concept

Related concepts

Sources

Open in the interactive atlas →