Model Card
Key facts. Model LiveGoalz Football 1X2 Forecaster, version det-2026-06-15b (deterministic). Intended use: informational football match-outcome probabilities. Last updated 2026-06-17. No performance claim is made on this page — measured metrics are published on the performance page once a settled sample exists.
Model name and version
LiveGoalz Football 1X2 Forecaster, version det-2026-06-15b. A deterministic statistical model: the same inputs always yield the same probabilities, and each version is pinned to a frozen benchmark.
Intended use
- provide informational probability estimates for football match outcomes;
- let readers compare model probabilities with bookmaker-implied probabilities at the same horizon;
- support research and analysis of match forecasting.
Non-intended use
- not financial, investment or betting advice;
- not a guarantee of any result;
- not for anyone at risk of gambling-related harm;
- not a replacement for a reader’s own judgement.
Backtest and forward-test
The deterministic rules were developed and checked against historical league and tournament fixtures, with results frozen as a regression benchmark so the model cannot silently change. Live, out-of-sample forecasts are being captured in a closed shadow ledger; a public settled sample will be published on the performance page once it is large enough to be meaningful. No result is reported here until that point.
Data-quality tiers
Every forecast carries a data-quality indication. Standard-tier forecasts have sufficient recent data for both teams. Data-limited forecasts (sparse recent data) have their confidence capped and are labelled as such, so a low-information estimate is never presented as a high-confidence one.
Evaluation metrics
These are the metrics that will be reported on the performance page once a settled sample exists. Definitions:
- Brier score — mean squared error between the predicted probabilities and the actual outcome; lower is better.
- Log loss — penalises confident wrong predictions more heavily; lower is better.
- Calibration — agreement between a stated probability and the observed frequency of that outcome.
- Market benchmark — the same metrics computed on bookmaker-implied probabilities at the same horizon, for comparison. No superiority over the market is claimed unless it is statistically supported.
Limitations and failure modes
- new teams or sparse data → capped confidence and a data-limited label;
- unusual fixtures (neutral venues, fixture congestion, heavy squad rotation) may not be fully captured;
- the model does not read team news beyond what recent form already reflects;
- high variance: even well-calibrated probabilities yield many wrong single-match calls.
Informational only. 18+. Please gamble responsibly.