Splits our home-side picks from our away-side picks. If one side wins markedly more than the other, the model is mis-pricing home-court advantage.
MLBAway win
Win rate47.1%
Hits / attempts8 / 17
MLBAway win
Win rate37.5%
Hits / attempts3 / 8
MLBHome win
Win rate51.9%
Hits / attempts304 / 586
MLBHome win
Win rate50.9%
Hits / attempts167 / 328
NBAHome win
Win rate43.8%
Hits / attempts7 / 16
NBAHome win
Win rate66.7%
Hits / attempts4 / 6
Last 7 days
Recent trend
Moneyline · win rate
League
Model
Win rate
Hits / attempts
Settled
Avg confidence
MLB
elo-v1
47.6%
40 / 84
84
53.3%
Total · MAE error
League
Model
MAE
Bias
Scored
Avg confidence
MLB
poisson-v1
3.69
+0.06
84
66.5%
Last 30 days
Monthly trend
Moneyline · win rate
League
Model
Win rate
Hits / attempts
Settled
Avg confidence
MLB
elo-v1
50.9%
170 / 334
334
53.5%
MLB
elo-v1.1
53.3%
106 / 199
199
53.5%
Total · MAE error
League
Model
MAE
Bias
Scored
Avg confidence
MLB
poisson-v1
3.60
+0.31
334
66.8%
Season
All-time
Moneyline · win rate
League
Model
Win rate
Hits / attempts
Settled
Avg confidence
MLB
elo-v1
51.7%
312 / 603
603
53.5%
MLB
elo-v1.1
50.6%
170 / 336
336
53.5%
NBA
elo-v1
Sample too small (n=16)
7 / 16
16
63.0%
NBA
elo-v1.1
Sample too small (n=6)
4 / 6
6
58.7%
Total · MAE error
League
Model
MAE
Bias
Scored
Avg confidence
MLB
poisson-v1
3.58
+0.03
603
66.8%
NBA
poisson-v1
Sample too small (n=16)
+0.91
16
93.3%
Perfect calibration
Confidence calibration
When we say '70% to win,' how often do those teams actually win? Points hugging the dashed line mean the model's confidence is honest. Blue = beats prediction (under-confident), red = worse than prediction (over-confident), green = within ±5%.
Moneyline model · 961 settled games (voids excluded)