β Eredivisie 2022-23 Β· Sun, Feb 26, 03:45 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 |
|---|
| PSV win | 59% | 64% | 1.65 | value: +6% |
| Draw | 24% | 18% | 4.13 | fair |
| FC Twente '65 win | 17% | 18% | 5.75 | value: +4% |
across 3 bookmakers Β· probabilities de-vigged (bookmaker margin removed)
Asian handicap
| Outcome | Market says | Best price |
|---|
| FC Twente '65 β1 | 54% | 1.81 |
| PSV β1 | 46% | 2.10 |
across 2 bookmakers Β· probabilities de-vigged (bookmaker margin removed)
Will there be 3 or more goals?
| Outcome | Market says | Model says | Best price | Verdict |
|---|
| Over | 54% | 54% | 1.81 | fair |
| Under | 46% | 46% | 2.08 | 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 | 0 |
| 14 | Shots | 14 |
| 9 | On target | 8 |
| 6 | Corners | 5 |
| 11 | Fouls | 8 |
| 1 | Yellow cards | 1 |
| 0 | Red cards | 0 |
Pre-match form
What each side looked like walking in β computed only from games before this one.