Scoring Rules for Performative Binary Prediction
Machine Learning
2022-07-08 v1 Artificial Intelligence
Abstract
We construct a model of expert prediction where predictions can influence the state of the world. Under this model, we show through theoretical and numerical results that proper scoring rules can incentivize experts to manipulate the world with their predictions. We also construct a simple class of scoring rules that avoids this problem.
Cite
@article{arxiv.2207.02847,
title = {Scoring Rules for Performative Binary Prediction},
author = {Alan Chan},
journal= {arXiv preprint arXiv:2207.02847},
year = {2022}
}
Comments
4 pages, accepted to workshop on Strategic Machine Learning at NeurIPS 2021