Proper scoring rules for estimation and forecast evaluation
Statistics Theory
2026-05-12 v4 Machine Learning
Statistics Theory
Abstract
Proper scoring rules have been a subject of growing interest in recent years, not only as tools for evaluation of probabilistic forecasts but also as methods for estimating probability distributions. In this article, we review the mathematical foundations of proper scoring rules including general characterization results and important families of scoring rules. We discuss their role in statistics and machine learning for estimation and forecast evaluation. Furthermore, we comment on interesting developments of their usage in applications.
Cite
@article{arxiv.2504.01781,
title = {Proper scoring rules for estimation and forecast evaluation},
author = {Kartik Waghmare and Johanna Ziegel},
journal= {arXiv preprint arXiv:2504.01781},
year = {2026}
}