World Cup 2026 contextual model card

Match Lab separates public match facts from model estimates. The model is designed to explain why a fixture may tilt one way, not to guarantee a result or encourage betting.

Current version

wc-analytics-v2.1-agentic-202606160800 · generated from public schedule, team, squad, result, and stable venue-profile data.

Inputs used

• team radar weighted quality
• FIFA ranking context
• key-player impact
• squad experience
• recent tournament form
• attack-versus-defense matchup
• venue climate and altitude adaptation
• travel and rest-day load
• style matchup volatility
• group-stage pressure
• pre-match-only table state
• scenario-sensitive Agent explanation
• rolling post-match calibration

How the Agent uses it

The Cloudflare Worker wakes on a cron schedule, checks the next post-match windows, overlays verified public corrections when upstream caches lag, rebuilds contextual predictions, and keeps Pages functions reading the live package first with static data as fallback.

Known limits

• Weather is currently represented by stable venue climate profiles, not minute-by-minute forecast feeds.
• Injuries, suspensions, confirmed lineups, and late rotation are not guaranteed unless public sources expose them reliably.
• Predictions are informational estimates only and must not be treated as betting, financial, legal, or medical advice.

Next model upgrades

• Live weather values: temperature, humidity, wind, rain, roof status, and kickoff-time changes.
• Lineup and absence layer: injuries, suspensions, expected XI, and squad rotation risk.
• Calibration log: compare pre-match estimates against finished results and track model drift.