Team ratings
Model 'deep', fitted through 18 September 2026
The model serving this sport has not been backtested.
Nothing here has been checked against what actually happened, so treat every
number as untested until you have run
python -m pipeline.backtest --sport baseball.Reading the ratings
Both numbers are on the log scale the model works in.
Attack higher = scores more. Defence lower = concedes
fewer, so a negative defence rating is a good thing.
Net is attack minus defence and ranks overall strength.
Ratings are fitted per league and are not comparable across them — a Bundesliga
+0.5 and a Serie A +0.5 do not mean the same thing.
| # | Team | Attack | Defence | Net | Strength |
|---|---|---|---|---|---|
| 1 |
|
+0.125 | +1.343 | -1.218 | |
| 2 |
|
-0.024 | +1.340 | -1.364 | |
| 3 |
|
-0.088 | +1.391 | -1.480 | |
| 4 |
|
-0.006 | +1.532 | -1.538 | |
| 5 |
|
+0.048 | +1.587 | -1.540 | |
| 6 |
|
-0.009 | +1.613 | -1.623 |
Both figures are on the log scale used inside the model. Higher attack means more goals scored; lower defence means fewer conceded, so net = attack − defence ranks overall strength.