Probable StatsCollege basketball, rated
Menu
Sign in to make your calls

Updated Thu 5 Nov, 4:27 PM ET

Scores, schedules and lines from ESPN; past seasons from sportsdataverse. Not affiliated with any team, league or bookmaker.

Scorecard

How the model would have done on past seasons, predicting every game the morning it was played using only earlier games, and how it is doing this season.

Updated Thu 5 Nov, 4:27 PM ET

Men's

Picks right, past seasons73.0%70,802 games, 2013-14 to 2025-26
Log loss0.523Lower is better; 0.693 is a coin flip
Average margin error8.8 pointsPredicted against final margin
This season85.3%128 of 150 picks, 2 of 3 logged before tip-off

Picks right by season

Every game held out
68%70%72%74%76%78%2013-142019-202025-2668%70%72%74%76%78%2013-142019-202025-26

Are the chances honest?

Home win chance against how often the home team won
0%0%25%25%50%50%75%75%100%100%Predicted 6.4%, won 4.8% of 825 gamesPredicted 15.6%, won 16.3% of 2,285 gamesPredicted 25.3%, won 25.3% of 3,869 gamesPredicted 35.3%, won 36.9% of 5,614 gamesPredicted 45.3%, won 46.0% of 7,318 gamesPredicted 55.1%, won 56.2% of 9,219 gamesPredicted 65.0%, won 65.3% of 10,253 gamesPredicted 75.0%, won 74.3% of 10,630 gamesPredicted 85.0%, won 85.1% of 10,037 gamesPredicted 95.3%, won 95.5% of 10,752 games0%0%25%25%50%50%75%75%100%100%Predicted 6.4%, won 4.8% of 825 gamesPredicted 15.6%, won 16.3% of 2,285 gamesPredicted 25.3%, won 25.3% of 3,869 gamesPredicted 35.3%, won 36.9% of 5,614 gamesPredicted 45.3%, won 46.0% of 7,318 gamesPredicted 55.1%, won 56.2% of 9,219 gamesPredicted 65.0%, won 65.3% of 10,253 gamesPredicted 75.0%, won 74.3% of 10,630 gamesPredicted 85.0%, won 85.1% of 10,037 gamesPredicted 95.3%, won 95.5% of 10,752 games

Against the betting market

2,983 games from 2024-25 and 2025-26 with a closing line
Picks rightLog lossMargin errorTotal error
This model72.8%0.5199.113.2
Closing line73.8%0.5129.012.8
An even mix of the two—0.513——

The closing line is the sharper forecast: it picks 1.0 points more games right and its log loss is 0.008 lower. Mixing the model into the line does not improve it, so the line already contains what the model knows.

By part of the season

Past seasons
GamesPicks rightLog loss
November13,39877.2%0.460
December13,12676.6%0.469
January to March44,19570.6%0.559
NCAA tournament80171.0%0.541

November is easiest: many games pit strong teams against weak ones. Conference play and the tournament match teams of similar strength.

Season by season

Each season scored with settings fitted on the others
SeasonGamesPicks rightLog lossBrier scoreMargin errorTotal points error
2025-265,75272.0%0.5210.1779.113.8
2024-255,76472.9%0.5190.1768.913.0
2023-245,72672.3%0.5380.1829.013.2
2022-235,72171.8%0.5400.1828.913.3
2021-225,50372.5%0.5250.1778.813.5
2020-213,86871.1%0.5430.1869.313.4
2019-205,32872.8%0.5270.1778.913.4
2018-195,60373.6%0.5200.1758.913.6
2017-185,54074.2%0.5160.1738.813.7
2016-175,52173.2%0.5190.1758.713.6
2015-165,46973.7%0.5130.1738.613.9
2014-155,49973.6%0.5170.1748.413.4
2013-145,50874.3%0.5110.1718.313.7

Women's

Picks right, past seasons76.9%41,259 games, 2018-19 to 2025-26
Log loss0.466Lower is better; 0.693 is a coin flip
Average margin error9.6 pointsPredicted against final margin
This season82.6%119 of 144 picks, 5 of 6 logged before tip-off

Picks right by season

Every game held out
72%74%76%78%80%2018-192022-232025-2672%74%76%78%80%2018-192022-232025-26

Are the chances honest?

Home win chance against how often the home team won
0%0%25%25%50%50%75%75%100%100%Predicted 4.9%, won 5.0% of 2,513 gamesPredicted 15.1%, won 15.1% of 2,533 gamesPredicted 25.0%, won 26.4% of 2,900 gamesPredicted 34.9%, won 33.7% of 3,209 gamesPredicted 45.2%, won 45.0% of 3,581 gamesPredicted 55.1%, won 55.4% of 3,950 gamesPredicted 65.0%, won 62.9% of 4,345 gamesPredicted 75.1%, won 75.2% of 4,707 gamesPredicted 85.1%, won 85.7% of 5,128 gamesPredicted 96.2%, won 96.3% of 8,393 games0%0%25%25%50%50%75%75%100%100%Predicted 4.9%, won 5.0% of 2,513 gamesPredicted 15.1%, won 15.1% of 2,533 gamesPredicted 25.0%, won 26.4% of 2,900 gamesPredicted 34.9%, won 33.7% of 3,209 gamesPredicted 45.2%, won 45.0% of 3,581 gamesPredicted 55.1%, won 55.4% of 3,950 gamesPredicted 65.0%, won 62.9% of 4,345 gamesPredicted 75.1%, won 75.2% of 4,707 gamesPredicted 85.1%, won 85.7% of 5,128 gamesPredicted 96.2%, won 96.3% of 8,393 games

Against the betting market

916 games from 2024-25 and 2025-26 with a closing line
Picks rightLog lossMargin errorTotal error
This model82.2%0.3729.813.4
Closing line82.6%0.3699.412.6
An even mix of the two—0.365——

The closing line is the sharper forecast: it picks 0.4 points more games right and its log loss is 0.003 lower. An even mix of the two (0.365) beats the line alone, so the model knows something the line misses; on 916 games that is suggestive, not proof.

By part of the season

Past seasons
GamesPicks rightLog loss
November7,88079.5%0.419
December7,20579.3%0.419
January to March26,13175.4%0.493
NCAA tournament46180.3%0.403

November is easiest: many games pit strong teams against weak ones. Conference play and the tournament match teams of similar strength.

Season by season

Each season scored with settings fitted on the others
SeasonGamesPicks rightLog lossBrier scoreMargin errorTotal points error
2025-265,62577.2%0.4500.1499.612.7
2024-255,28977.5%0.4460.1489.512.8
2023-245,57077.3%0.4650.1549.613.0
2022-235,52477.0%0.4660.1549.513.1
2021-225,22676.8%0.4780.1589.513.4
2020-213,47174.0%0.5000.1689.813.5
2019-205,17176.2%0.4770.1599.613.1
2018-195,38377.7%0.4580.1519.413.4