Brier score

A proper scoring rule that measures probabilistic forecast accuracy as the mean squared difference between predicted probabilities and binary outcomes; lower scores indicate better calibration.

Cluster: Information Theory

Related Concepts

• superforecasting — Techniques and traits of forecasters who consistently outperform base rates and prediction markets.
• calibration — When stated probabilities match empirical frequencies—e.g., events given 70% odds happen 70% of the time.
• forecasting accuracy — Measuring how well predicted probabilities match actual outcome frequencies over many events.

Articles about Brier score

• How Well Can Large Language Models Predict the Future? by Forecasting Research Institute