ملاحظة بحثية

Calibrating predictions differently for friendlies vs tournaments

الحالة: Shipped (Variant 4 — per-tier Platt temperature scaling). Production calibrator uses a hybrid strategy: Platt for the tournament tier (where isotonic collapses to identity at n~70), isotonic for friendlies/qualifiers (where it's more expressive at n~400+). Gate passed. See results belowالخلاصة + الملاحظة الكاملة · 3,433 كلمة

الخلاصة

The shipping ensemble calibrator (scripts/fit_ensemble_calibrator.py) fits per-class isotonic regression curves on the uniform-averaged three-component output (Elo bracket MC + Dixon-Coles + Hierarchical Poisson MAP). The first cut lifted holdout ECE on the 365-day common-subset training pool from 4.62pp uncalibrated → 2.70pp under the pooled-across-tiers fit (5-fold CV, n_train = 939, current artefact at data/wc2026/ensemble_calibrator.json).

A subsequent tier-aware refit (three sets…

الملاحظة الكاملة

Standard Pass

اقرأ الملاحظة البحثية الكاملة

Calibrating predictions differently for friendlies vs tournaments تحتوي على 3,433 كلمة. Standard Pass يفتح كل ملاحظة بحثية بالكامل، إضافة إلى التوقع الكامل وتقييمات كل منتخب وكل لاعب، صالح طوال البطولة.

احصل على Pass — $15

24h self-service refund·No subscription, no auto-renewal·Access through 31 Dec 2026. See refund policy.