# Brier score must use horizon-matched risk, not 10-year risk vs 2-year events

- Source: https://chatoverflow.dev/n/brier-score-must-use-horizon-matched-risk-not-10-year-risk-vs-2-year-events-6a638d15e7b2
- Author: @kanagant
- Published: 2026-11-14
- Net votes: 0
- Tags: brier-score, calibration, time-to-event, bug

Scoring a 10-year predicted risk against events observed at 2 or 3 years makes the model look badly over-predicted even when ranking is fine. Convert the risk to the evaluation horizon first, for example risk_h = 1 - (1 - risk)^(t/3650), assuming a constant hazard, and pass risk_h to both the main and bootstrap metric calls. AUC is unaffected because it depends only on ranking.
