← All data & metrics Experimental · Frozen source
NFL game forecasts & backtests 11,978 data points · 1,562 fields
Full JSON Download all CSV ↓ Metric formulas & meanings Signal or noise · historical research
What the backtests support These verdicts summarize the frozen 2024–2025 evaluation. They do not promote experimental forecasts into current recommendations. A single correct pick is not proof of a repeatable pattern.
One game
No single-game verdict 80% margin range: ±18.0 points; observed coverage 82.3%
A single upset or correct pick cannot tell us whether a forecast has a lasting edge. Judge frozen predictions over many games.
The range is calibrated from historical errors; it does not capture every roster or injury change.
Across games
Measured pooled edge over Elo Model − Elo Brier -0.0078; 95% block interval -0.0140 to -0.0018 (n=569)
Lower Brier is better. The paired interval stays below zero across the pooled held-out games.
This is a historical model comparison, not proof of an advantage on the next matchup.
Across seasons
Consistency still mixed 1 of 2 seasons have a model-favoring 95% interval versus Elo
2024: -0.0139 to 0.0042 · 2025: -0.0186 to -0.0024
Only the evaluated seasons are represented. More unseen seasons and model-change controls are needed before calling this durable.
Player to next season
New signal not established Candidate MAE 3.103 vs age plus production 3.098 (3009 player-seasons)
The candidate does not beat the strongest existing baseline on this point-error measure.
Inspected historical seasons and excluded rookie or thin-history cohorts limit any claim about next-season skill.
Historical market check
Market ahead on paired subset Model − market Brier 0.0107; 95% block interval 0.0040 to 0.0185
Positive values favor the historical market on games with matched odds.
Historical odds lack archived quote times. This is not evidence of a real-time or tradable edge.
Evidence metadata Frozen artifact d5b0aa30726c · Snapshot Sep 5, 2026, 1:00 AM UTC
Read the compact evidence API
Players, teams & metrics All data points Field dictionary This-page CSV uses field path, type and value columns, including source context. Full dataset downloads are above.
11,978 matches · 5601–5650 shown. Every field remains available in the full download. Filters are saved in this page’s address.
Recorded data points Field path Value & type $["games"][100]["gameId"] 2026_07_SF_ATL string $["games"][100]["gameType"] REG string $["games"][100]["gameday"] 2026-10-25 string $["games"][100]["homeMarginInterval80"][0] -16.86990672671327 number $["games"][100]["homeMarginInterval80"][1] 19.197320270067504 number $["games"][100]["homeTeam"] ATL string $["games"][100]["homeWinProbability"] 0.5274315672598434 number $["games"][100]["kickoff"] 2026-10-25T17:00:00Z string $["games"][100]["market"] Unavailable (null) null $["games"][100]["neutral"] false boolean $["games"][100]["totalInterval80"][0] 29.58012844750329 number $["games"][100]["totalInterval80"][1] 62.29374607202485 number $["games"][100]["week"] 7 number $["games"][101]["awayTeam"] TB string $["games"][101]["eloProbability"] 0.5282442238201682 number $["games"][101]["expectedAwayScore"] 21.648172747142716 number $["games"][101]["expectedHomeMargin"] 0.6097082961438769 number $["games"][101]["expectedHomeScore"] 22.257881043286595 number $["games"][101]["expectedTotal"] 43.90605379042931 number $["games"][101]["featureValues"]["allowedDifference"] 1.2937694254656833 number $["games"][101]["featureValues"]["allowedSum"] 45.64160806104683 number $["games"][101]["featureValues"]["awayGames"] 0 number $["games"][101]["featureValues"]["awayRest"] 7 number $["games"][101]["featureValues"]["eloDifference"] -35.352987797023616 number $["games"][101]["featureValues"]["homeField"] 1 number $["games"][101]["featureValues"]["homeGames"] 0 number $["games"][101]["featureValues"]["homeRest"] 7 number $["games"][101]["featureValues"]["marginDifference"] -1.3488229268016427 number $["games"][101]["featureValues"]["restDifference"] 0 number $["games"][101]["featureValues"]["scoringDifference"] -0.05505350133595854 number $["games"][101]["featureValues"]["scoringSum"] 41.315557760264426 number $["games"][101]["featureValues"]["winRateDifference"] -0.04227301332357564 number $["games"][101]["gameId"] 2026_07_TB_CAR string $["games"][101]["gameType"] REG string $["games"][101]["gameday"] 2026-10-25 string $["games"][101]["homeMarginInterval80"][0] -17.42390520224651 number $["games"][101]["homeMarginInterval80"][1] 18.643321794534263 number $["games"][101]["homeTeam"] CAR string $["games"][101]["homeWinProbability"] 0.5223135520684741 number $["games"][101]["kickoff"] 2026-10-25T17:00:00Z string $["games"][101]["market"] Unavailable (null) null $["games"][101]["neutral"] false boolean $["games"][101]["totalInterval80"][0] 27.54924497816853 number $["games"][101]["totalInterval80"][1] 60.26286260269009 number $["games"][101]["week"] 7 number $["games"][102]["awayTeam"] DEN string $["games"][102]["eloProbability"] 0.3865782884989143 number $["games"][102]["expectedAwayScore"] 25.562414026008096 number $["games"][102]["expectedHomeMargin"] -6.717977626942151 number $["games"][102]["expectedHomeScore"] 18.844436399065945 number
← Previous Page 113 of 240 Next → Dataset details Source date: Sep 5, 2026, 1:00 AM UTC
272 scheduled games, 32 team outlooks, probability calibration, score errors and player-production experiments. Frozen preseason research; does not change public rankings.
Original capture date; opening or downloading does not refresh the source. Per-record timestamps take precedence. Definitions may describe unavailable inputs.
How to read and verify this data JSON bracket paths; [] means every array element. CSV uses concrete zero-based indices. Types are observed, not a promise that future fields cannot change. null is unavailable; empty array/object means an empty collection. Zero is preserved as a measured or supplied numeric value. Source-native units and scoring. Consult metric-definitions for formulas; ambiguous units remain unspecified, never inferred.
sha256 of UTF-8 JSON.stringify(data), excluding this envelope. Source receipt hashes remain inside data. CSV prefixes formula-looking text with an apostrophe; numeric signs are preserved. JSON keeps original strings.
ecbde32e2751aef21c0bf12e3dfcd6ef10021f583afb03d6db2f3bce002f9316
Published observations, approved source-labeled aggregates, research and definitions are provided within each dataset's stated scope. Read each record's source, period, scoring and availability. Research visibility does not promote a model into public rankings. Missing means unavailable, never zero. No account records or provider write access.