Model Lab

Every EdgeIQ model version is stored and graded against completed games. Historical predictions are never overwritten and weak results are published alongside strong ones.

Chronological backtesting

These evaluations only use information available before each game and test each version on later, unseen games.

NFL watchlist

NFL games to watch

Upcoming matchups where the baseline model estimates one team at 70% or higher, with historical context for the same confidence level.

View full board

These are statistical estimates for research and games worth closer analysis—not betting recommendations or guaranteed outcomes. Model probability is not the same as historical accuracy.

Live and historical model records

This archive is separate from the chronological backtest above. Headline rates appear only after at least 30 graded games.

EdgeIQ Baseline

vv1.0.0
active
NBA

Gradient-style baseline blending team power ratings, recent form, home advantage, rest and pace, with logistic probability calibration.

Sample

1390

Accuracy

69%

Brier

0.256

Log loss

1.129

Mean abs. error

27.14

Model performance detail

Pro feature

Month-by-month accuracy trends and the full calibration breakdown for this model version, so you can see how closely stated confidence matched real outcomes.

Your plan: Free · Unlocks with Pro — $7.98/month

Metrics are statistical measures of past performance on a limited sample. They describe how the model has behaved historically and do not guarantee future results.

EdgeIQ Baseline

vv1.0.0
active
MLB

Gradient-style baseline blending team power ratings, recent form, home advantage, rest and pace, with logistic probability calibration.

Sample

2981

Accuracy

58%

Brier

0.272

Log loss

0.791

Mean abs. error

5.08

Model performance detail

Pro feature

Month-by-month accuracy trends and the full calibration breakdown for this model version, so you can see how closely stated confidence matched real outcomes.

Your plan: Free · Unlocks with Pro — $7.98/month

Metrics are statistical measures of past performance on a limited sample. They describe how the model has behaved historically and do not guarantee future results.

EdgeIQ Baseline

vv1.0.0
active
NHL

Gradient-style baseline blending team power ratings, recent form, home advantage, rest and pace, with logistic probability calibration.

Sample

1502

Accuracy

61%

Brier

0.237

Log loss

0.674

Mean abs. error

2.82

Model performance detail

Pro feature

Month-by-month accuracy trends and the full calibration breakdown for this model version, so you can see how closely stated confidence matched real outcomes.

Your plan: Free · Unlocks with Pro — $7.98/month

Metrics are statistical measures of past performance on a limited sample. They describe how the model has behaved historically and do not guarantee future results.

EdgeIQ Baseline

vv1.0.0
active
NCAA Football

Gradient-style baseline blending team power ratings, recent form, home advantage, rest and pace, with logistic probability calibration.

Sample

4406

Accuracy

76%

Brier

0.176

Log loss

0.534

Mean abs. error

23.55

Model performance detail

Pro feature

Month-by-month accuracy trends and the full calibration breakdown for this model version, so you can see how closely stated confidence matched real outcomes.

Your plan: Free · Unlocks with Pro — $7.98/month

Metrics are statistical measures of past performance on a limited sample. They describe how the model has behaved historically and do not guarantee future results.

EdgeIQ Baseline

vv1.0.0
active
NCAA Basketball

Gradient-style baseline blending team power ratings, recent form, home advantage, rest and pace, with logistic probability calibration.

Sample

6237

Accuracy

75%

Brier

0.168

Log loss

0.506

Mean abs. error

19.35

Model performance detail

Pro feature

Month-by-month accuracy trends and the full calibration breakdown for this model version, so you can see how closely stated confidence matched real outcomes.

Your plan: Free · Unlocks with Pro — $7.98/month

Metrics are statistical measures of past performance on a limited sample. They describe how the model has behaved historically and do not guarantee future results.

EdgeIQ NFL Performance

vv2.0.0
active
NFL

NFL projection from recent scoring, weighted form, home/away splits, opponent strength and rest.

Sample

1966

Accuracy

61%

Brier

0.234

Log loss

0.661

Mean abs. error

15.55

Model performance detail

Pro feature

Month-by-month accuracy trends and the full calibration breakdown for this model version, so you can see how closely stated confidence matched real outcomes.

Your plan: Free · Unlocks with Pro — $7.98/month

Metrics are statistical measures of past performance on a limited sample. They describe how the model has behaved historically and do not guarantee future results.

Community models

Models built by EdgeIQ members and published after review. Each one is graded on the same held-out games as the EdgeIQ baseline.

No community models have been published yet. Build one in the workbench and request publication.