Brier Score
Updated 2026-08-15
INTRODUCTION
English translation pending.
CORE DEFINITION
The Brier score measures the accuracy of a probabilistic forecast as the average squared difference between the predicted probability and the actual outcome, coded as 0 or 1, across all events. A lower score means a more accurate forecast, and 0 is perfect. It gives an objective measurement of whether a forecast is really accurate, which is what calibrating personal judgment requires.
SCAFFOLDING EFFECT
Reduce cognitive load
- Collect the pairs: gather each predicted probability with the outcome that occurred. - Take the mean squared gap: compute the score across all the events. - Compare on one scale: use the score to rank models or forecasters against each other.
Anchor fast decisions
Squaring the error makes every miss positive and punishes confident misses harder than hesitant ones, so the score penalizes the overconfidence a raw error measure would let hide. Averaging over events turns a run of forecasts into one number on a common scale, which is what makes different forecasters comparable at all.
MINIMUM ACTION
In progress 0/1Practice this model in one real situation:
account_treeGenealogyexpand_more
menu_bookReferencesexpand_more
Source support: Explicit
- en.wikipedia.orghttps://en.wikipedia.org/wiki/Brier_scoreverified
PRIVATE NOTES · Only visible to you
SAVED Q&A
ENTRY Q&A · Private saving available
Ask with a clear boundary
thinkingmodels answers from published entry context only.
Your question is sent to thinkingmodels. The answer uses public entry context only.
RELATED MODELS