Cooper Predictor U is a statistical college football model covering FBS, FCS, Division II, Division III and NAIA. Each level model is built and tested separately.
In walk-forward validation the model is trained only on seasons that came before the season being tested. That keeps future results out of the inputs and gives an honest measure of how the model would have performed at the time.
Its central feature is the power rating — an estimate of how a team would perform against a reference opponent within its own level. That rating produces:
The goal is not to restate the rankings you see elsewhere. It is to produce an independent answer, publish it, and measure how well it performs.
Not a recruiting ranking. A team does not move up for having more highly rated prospects or a more recognizable name. Talent shows up in on-field performance, but recruiting rankings and roster reputation are not model inputs.
Not a media poll. There are no ballots, reputation votes or manual adjustments to force the rankings into a more familiar order. When the model disagrees with the consensus, the disagreement stands and gets tested by future results.
Not a guarantee. A team with a 70% win probability still has a meaningful chance to lose. Favorites lose and upsets happen — that's what makes the sport fun.
Not finished. New games create new evidence and ratings move as the season develops. The largest swings come in the opening weeks, when each result adds the most information.
The model evaluates what teams have done on the field, the quality of the opponents they faced, and how those performances compare across their level. It uses opponent-adjusted scoring, schedule strength, classification context and — once a season is underway — recent form.
That context matters because identical records tell very different stories. Going 9-1 against a demanding schedule is not equivalent to going 9-1 against a weak one. The model reads the performances behind the record rather than the win-loss column alone.
Scoring margin matters, but extreme margins are compressed rather than rewarded point for point. Beating a strong opponent says more than adding late points against an overmatched one. The difference between winning by 20 and winning by 50 is much smaller in the model's eyes than the scoreboard suggests.
Preseason ratings are built from on-field evidence available before the new season — no recruiting rankings, no subjective roster adjustments. Once games begin, current-season results blend in and gradually take on more weight.
The win probability is the most useful week-to-week output: it quantifies how confident the model is, and how big an upset would be. In a projection with a 62% win probability, the 62% is the important number, not the exact score. The favorite still has a meaningful chance to lose.
Calibration is measured across groups of historical predictions, not by replaying one game a hundred times. The percentages are graded against held-out seasons so stated confidence can be compared with what actually happened.
For FBS, the Predictor simulates the remaining schedule and projects the 12-team College Football Playoff field. The published CFP committee ranking is not a formula, so the forecast uses a disclosed resume proxy built from record, schedule strength, quality wins and Cooper power.
The 2026 selector guarantees the ACC, Big 12, Big Ten and SEC champions, the highest-ranked team from the six other FBS conferences, and Notre Dame when projected in the top 12, then fills the field by projected ranking. Weekly calibration was validated against the 2024 and 2025 12-team fields; the exact 2026 automatic-bid contract is new and has no direct historical season.
An independent model is most valuable when it disagrees with the consensus. The Predictor uses proprietary statistics and independently trained coefficients, so no other system will reproduce the exact ratings. Where it differs sharply from other rating systems, those are the teams whose seasons will teach us the most — a gap does not prove either system right or wrong.
Some picks will be wrong. The difference offered here is transparency: every posted pick stays public, results get tracked, accuracy gets published, and the misses get discussed alongside the wins. Quietly deleting a bad prediction would make the whole exercise meaningless. The model should earn trust through transparent results, not claims or name recognition.
College football extends far beyond the teams that dominate national television. Cooper Predictor U covers five levels so the same transparent ratings, projections and accountability reach programs across the sport.
FBS has a modeled 12-team CFP field, and FCS has a modeled 24-team NCAA Championship field. Division II, Division III and NAIA postseason odds will be added only when their automatic bids and committee selections can be reconstructed and validated honestly.