| Figure | Philadelphia Union | Toronto FC | What it means |
|---|---|---|---|
| N — no-draw run | 8 | 6 | matches in a row without a draw |
| Max N | 18 | 17 | this team's longest run ever |
| E — draw debt | 1.70 | 2.14 | expected draws over the current run |
| p50 — last 50 | 20.0% | 44.0% | draw rate over its last 50 matches |
| p100 — last 100 | 22.0% | 30.0% | draw rate over its last 100 matches |
| Draw % — all time | 25.7% | 25.8% | share of every match drawn |
| Draw score | 0.385 | 0.371 | the predictor ranking score |
| Rank | 222 | 252 | position in that ranking |
| Σ N | 14 | both sides' runs added | |
| Σ E | 3.83 | both sides' draw debt added | |
| Σ Score | 0.755 | what the Cross predictor orders by | |
The mix is the one that scored best over 544,576 matches — the two are averaged on the log-odds scale, not simply added.
A regression over five signals — the goals model, the draw rate at this Elo gap, the expected goals in the fixture and the competition's own base draw rate — with an isotonic map on top to put the level back where reality is. Held out on a decade it never saw it beat the blend above, which is why both are shown here while one is chosen. This is a real forecast: the fixture had not been played when the model was fitted.
A forecast from every match played so far. Measured over 160,869 priced matches the goals model is slightly worse than the bookmakers (how it is scored), so a high draw chance means an even, low-scoring match rather than value. Descriptive statistics, not betting advice.