WIN
New Mexico State Aggies at Florida International Panthers
Under 46.5
Locked record →South Ark Daily Picks / Model Performance & Prediction History
Model Performance & Prediction History
Measured chronological backtests and an immutable forward prediction ledger, kept separate from betting results.
Model Record
Performance & filters →CFB counts official selections plus the owner-retained opening-night pick; the strict pregame record is separate on the ledger. Professional rows count first-published winner forecasts, not betting results. Units and ROI require recorded prices and stakes.
| Sport / record type | W–L–P | Pending | Win % | Units / ROI |
|---|---|---|---|---|
| College Football · tracked | 2–0–0 | 0 | 100.0% | Unavailable |
| NFL · research winners | 0–0–0 | 29 | Unavailable | Unavailable |
| NBA · research winners | 0–0–0 | 14 | Unavailable | Unavailable |
| NHL · research winners | 0–0–0 | 98 | Unavailable | Unavailable |
| MLB · research winners | 0–0–0 | 0 | Unavailable | Unavailable |
Recent Results
Research backtests
| Sport | History | Latest final | Test season / games | Score MAE | Brier | Log loss |
|---|---|---|---|---|---|---|
| NFL | 919 | 2026-10-05 | 2026 / 64 | 7.7 | 0.226 | 0.642 |
| NBA | 1326 | 2026-06-13 | 2025 / 1228 | 9.7 | 0.218 | 0.626 |
| NHL | 1449 | 2026-10-07 | 2026 / 55 | 1.5 | 0.240 | 0.673 |
| MLB | 7289 | 2025-09-28 | 2025 / 2425 | 2.5 | 0.246 | 0.686 |
Score MAE is mean absolute error per team; lower is better. Brier and log loss evaluate home-win probability on decisive games. Each test prediction uses only earlier calendar dates; coefficients refit chronologically. Season thresholds are fixed in advance and not optimized on reported results.
Historical ingestion times are unavailable: calendar-date exclusion is a proxy, not evidence of point-in-time injury or roster coverage. The preserved NBA 2013–2015 and MLB 2023–2025 archives are historical studies. Once connected, the NBA model trains separately on API-SPORTS results; archive rows are retained. None establishes profitable betting performance.
Probability calibration
MLB
| Probability bin | Sample | Mean estimate | Observed home wins |
|---|---|---|---|
| 0.0%–20.0% | 0 | Unavailable | Unavailable |
| 20.0%–40.0% | 3 | 39.0% | 66.7% |
| 40.0%–60.0% | 2411 | 52.5% | 54.2% |
| 60.0%–80.0% | 11 | 61.0% | 72.7% |
| 80.0%–100.0% | 0 | Unavailable | Unavailable |
Forward prediction ledger
0 distinct graded professional games; 0 immutable forecast revisions. Revising a pregame estimate creates a new record rather than changing the original.
| Published | Sport / game | Original score | Team win probability | Result | Model |
|---|---|---|---|---|---|
| No frozen predictions in this filter yet. Backtests are kept separate. | |||||
Betting record, win percentage, ROI, units and closing-line value: unavailable until real priced picks are published and settled. No artificial betting record is inferred from score projections.
Preserved CFB original-line pick record and validation →