β Bundesliga 2005-06 Β· Sat, Mar 4, 03:00 PM UTC
The betting picturemarket vs our model, market by market
βMarketβ = what bookmaker prices imply after removing their margin β the world's best guess. βModelβ = what our machine-learning model said BEFORE this game, replayed honestly (it never saw the result). A bet is only interesting when the model sees something meaningfully more likely than the market does (the edge) β it's never about picking the winner.
Who wins? (90 minutes)
| Outcome | Market says | Model says | Best price | Verdict |
|---|
| Bayer 04 Leverkusen win | 36% | 37% | 2.50 | fair |
| SV Werder Bremen win | 36% | 46% | 2.62 | value: +21% |
| Draw | 28% | 17% | 3.40 | fair |
across 2 bookmakers Β· probabilities de-vigged (bookmaker margin removed)
The match in numberswhat happened + what each side looked like walking in
Match stats
| 1 | Half-time score | 1 |
| 8 | Shots | 6 |
| 3 | Corners | 4 |
| 18 | Fouls | 32 |
| 2 | Yellow cards | 2 |
| 0 | Red cards | 0 |
Pre-match form
What each side looked like walking in β computed only from games before this one.