NFL
Methodology
Each competition has its own independent model, weights, parameters, versions and performance history. Nothing is shared or copied between College Football and the NFL.
Active model version: 0.1.0 draft — engine revision engine-0.1.0. Predictions are disabled until every required parameter is set; unavailable states are shown instead of estimated numbers.
Rating construction
A team's base GDA Rating is a weighted combination of category grades. Weights must total exactly 100%.
| Category | Weight |
|---|---|
| No weights configured for this competition yet. | |
Weight total: 0.00% — invalid, so this version cannot be published.
From rating to model line
Predicted home margin = points-per-rating-unit × (home GDA Rating − away GDA Rating) + home-field points + home adjustment − away adjustment. Home-field points are excluded at neutral sites. A positive number favours the home team.
- Points per rating unit: not set
- Home-field points: not set
- Residual cap: not set
- Learning gain: not set
- Maximum single move: not set
- Update cadence: not set
Updates, freezing and honesty rules
- Predictions are frozen at kickoff along with the market line used, so published history can never be quietly rewritten.
- Rating changes are capped, and the winner's gain equals the loser's loss so the league stays balanced.
- Market lines are stored with their source and capture time. Where no line exists, the model edge is reported as unavailable rather than assumed.
- When a required input is missing, GameDay Advantage states exactly what is missing instead of estimating a number.