Brier Score
The Brier Score is a method for measuring the accuracy of probabilistic forecasts by comparing predicted probabilities with actual binary outcomes. For a single binary forecast: Brier Score = (Forecast Probability − Outcome)² where the outcome is: 1 if the event occurs and 0 if it does not. Lower scores indicate better performance.
Why it matters to you
The Brier Score rewards probability estimates that are both accurate and appropriately confident. Suppose you forecast: 70% and the event happens. Score: (0.70 − 1)² = 0.09 If you forecast: 90% and the event does not happen: (0.90 − 0)² = 0.81 The highly confident incorrect forecast is penalised much more heavily.
Terms that sit next to this one
See the prediction markets front
Live odds, what settles this week and five tools.