J1 2026-27 -- round of 2026-09-05

Match probabilities for Japan's J1 League. 10 fixtures, fixed before kickoff. The market is measurably better than this model — a disagreement below is a question, not an answer. Full caveat & numbers.

Calibrated model probabilities. Kickoff times are UTC, 2026. No market odds are shown here — see Methodology for why.
Kickoff Home Away P(H) P(D) P(A) Result
Sep 05 10:00 Avispa Fukuoka Mito 38.6% 28.5% 33.0% not yet played
Sep 06 09:00 Nagoya Grampus Machida 26.8% 25.6% 47.6% not yet played
Sep 06 09:00 Okayama Sanfrecce Hiroshima 23.1% 29.0% 47.9% not yet played
Sep 06 09:00 Chiba Gamba Osaka 20.5% 20.7% 58.8% not yet played
Sep 06 09:00 Kashima Antlers Urawa Reds 53.5% 23.7% 22.8% not yet played
Sep 06 10:00 Cerezo Osaka Verdy 47.5% 27.2% 25.3% not yet played
Sep 06 10:00 Kashiwa Reysol Yokohama F. Marinos 45.7% 23.8% 30.5% not yet played
Sep 06 10:00 Kawasaki Frontale Shimizu S-Pulse 55.4% 21.9% 22.6% not yet played
Sep 06 10:00 Vissel Kobe V-Varen Nagasaki 67.4% 19.3% 13.3% not yet played
Sep 06 10:30 FC Tokyo Kyoto 38.2% 25.2% 36.5% not yet played

Over 3,882 backtested J1 matches (2014–2025-26), the closing betting market scored 0.0044 RPS points better than this model on average (95% CI [0.0026, 0.0060]) — see Methodology. This model has no information the market lacks: it does not see injuries, lineups, suspensions or travel. The bold figure in each row is only the most likely of three outcomes, not advice — in most football matches the most likely single outcome still loses more often than it wins.

Metadata & verification

Published (UTC)
2026-09-03 07:41 UTC
Trained as of (UTC)
2026-09-03 07:40 UTC
Model version
footy-ev-phase2-dc-tb-v1
params_hash
ea317b1dbde414553b28ff026b02ecdc2ba3b088e5d242b6cff416d721ed3f7f
File SHA-256
055acb1e34963d57fe17313f2d6f8d66edb75af8125554203f44717518793899
Market snapshot SHA-256
77775fd20058457d7ebbacb425d6ccb0790a7ce12a702fdee0e00e2607ca8990
Training window
1792 matches, 29 teams, since 2021
Publish gate
PASS

How to verify

This file is committed as predictions/j1_2026_2026-09-05.json in the project's git repository, with the SHA-256 shown above. On its own, a git commit timestamp is not strong third-party evidence that a prediction existed before kickoff — the author can set it to any date. Independent timestamping (OpenTimestamps), Wayback Machine archiving and a GitHub Actions server-time witness are part of this project's published plan for closing that gap (design document, section 3) and are not yet wired into this build. Until they are, verify what you can today: recompute the SHA-256 of the committed file yourself and confirm it matches the value above, and read the raw JSON — nothing on this page is derived from anything else.