Data inputs
Each game prediction starts from a structured snapshot built at SSG time:
- Game metadata: tip-off time, arena, home/away, league, round.
- Recent form for each team (last 5 games, weighted by recency).
- Head-to-head record between the two teams over their last meetings.
- Home/away split — how each team performs at home and on the road.
- Probability distributions over the game winner, total points, and over/under markets.
For background on this metric, see Elo rating.
Models
Predictions are produced by an ensemble of large language models that consume the structured inputs above and output a calibrated probability distribution plus a short reasoning paragraph.
No single model decides a prediction. The pipeline aggregates outputs across models and falls back to the best-calibrated source if a candidate disagrees beyond a configured threshold. For the underlying probability model, see probability theory.
Prediction scoring
When you submit predictions your score is computed deterministically:
- 1 point for a correct outcome (home team win / away team win).
- 3 points for the exact final score.
Calibration
Prediction confidence is calibrated against historical results, not against the model's internal certainty. A 60% win probability means the model is right roughly 60% of the time on similarly framed games — not that the favourite will win. For the statistical concept, see Calibration (statistics).
Known limitations
Basketball has irreducible variance. The model has no view on injuries, rest days, or last-minute lineup news unless those signals are present in its training inputs. Predictions are best read alongside current news, not as a replacement for it.