The model's --use-xg path fits round(xG) as the per-match Poisson response in Dixon-Coles and Hierarchical Poisson (falling back to realised goals where xG is absent). It was structurally bounded by a tiny corpus: the JaseZiv FBref mirror that scripts/pull_intl_xg.py reads carries Opta xG for only 143 tournament matches — WC 2018 (64), Euro 2020 (51), Copa 2021 (28). WC 2022 is present-but-null there; Euro 2024 / Copa 2024 / AFCON 2023 are absent. With 143 xG-bearing matches out of ~49…
研究笔记
Back-filling international xG from StatsBomb open data
状态: Production xG path WIRED (2026-05-29) — `auto-refit.yml` fits DC with `--use-xg` and refits the calibrator on the xG-enabled ensemble; HP excluded (fails the gate's ECE half). The xG-enabled artefacts (`dixon_coles.json` / `ensemble_calibrator.json` / `data.json`) regenerate on the first auto-refit after merge (not hand-committed — see "Production wiring" for why). Single-provider corpus (314 StatsBomb + 28 residual Opta Copa-2021 = 342 rows). Gate clears for DC + Ensemble on both evaluation slices回测日期: 29 May 2026要点 + 全文 · 1,755 字
要点
全文
Standard Pass
阅读完整研究笔记
Back-filling international xG from StatsBomb open data 共 1,755 字。Standard Pass 解锁所有研究笔记全文, 以及完整预测和逐队、逐球员评分, 有效期至赛事结束。
Every forecast graded against the real result, scored on 987 matches since 2014. See the scorecard.
24h money-back, no questions asked·No subscription, no auto-renewal·Access through 31 Dec 2026. See refund policy.