build1 distinct publisher
Dividing by possession made the model worse, and only the second score showed it
A football similarity space scored 0.695 for possession contamination, and the obvious one-line normaliser only got it to 0.572. Subtracting a fitted line instead got 0.450.
Publishers:dev.to
Reality
- Evidence54
- Adoption
- Insufficient
- Hype gap−8
- Incentives32
- Confidence48