Data Sources

Data Sources and Model Boundaries

Last updated: 2026-06-15 · Applies to homepage, dashboard, blog, and match compare pages

Key Takeaway

The site separates public fixtures and scores, prediction files, score distributions, public match-center lineup data, and AI summaries. Probabilities, xG, score calls, and risk labels are model-assisted analysis, not official outcomes.

Core Data Tables

Fixtures and scoresdata/schedule.csv

Teams, dates, groups, host location, and completed scores once available.

Prediction probabilitiespredictions/game_predictions.csv

Win-draw-loss probability, expected goals, knockout probability, and score-distribution inputs.

Simulation outputpredictions/sim_results.csv

Group and knockout advancement probabilities, title probability, and finalist probability.

Lineups and playersPublic match centers

Starters, substitutes, formations, and player event stats appear only after the source publishes them.

What Is Estimated

Win probability, expected goals, recommended scorelines, total-goals leaning, BTTS, upset risk, AI final forecast, and post-match model-review conclusions are generated from prediction files and page logic.

What Is Public Fact

Completed scores, fixture dates, groups, host location, and published match-center lineup/player-event data are treated as public data. The site tries to show whether data is confirmed or still pending.

How AI Uses the Data

The AI forecast uses only provided model probabilities, score distributions, standings context, and public data summaries. It does not treat unavailable injuries, odds, weather, referees, or private team news as facts.

Related Pages

Methodology · Disclaimer · Match Compare · Dashboard