Porto vs Estoril — Primeira Liga forecast, Saturday, 31 October 2026
Metis Forecast
Independent model — no market priceModel updated
Porto
64%
Draw
23%
Estoril
13%
Expected goals
1.98–0.87
Porto · Estoril
Porto win 64% of the current Metis Forecast. Most likely scores: 2–0 (11.4%), 1–1 (10.8%), 1–0 (10.7%).More forecast detail +
Both teams score in 51% of simulations.
Those three cover 33% of outcomes; the other 67% is spread across every remaining scoreline.
Porto score at least twice in 59%; Estoril in 22%.
Scoreline distribution
Estoril goals →
| 0 | 1 | 2 | 3 | 4 | 5+ | |
|---|---|---|---|---|---|---|
| 0 | 6.6 | 4.2 | 2.2 | 0.6 | 0.1 | 0.0 |
| 1 | 10.7 | 10.8 | 4.3 | 1.2 | 0.3 | 0.1 |
| 2 | 11.4 | 9.9 | 4.3 | 1.2 | 0.3 | 0.1 |
| 3 | 7.5 | 6.5 | 2.8 | 0.8 | 0.2 | 0.0 |
| 4 | 3.7 | 3.2 | 1.4 | 0.4 | 0.1 | 0.0 |
| 5+ | 2.1 | 1.8 | 0.8 | 0.2 | 0.0 | 0.0 |
Rows: Porto goals · values are percentages
Match outcomes
Team scoring & clean sheets
Most likely scores
Market odds
| Market | over | under | Best |
|---|---|---|---|
| O/U 2.5 | |||
Reference prices, published with the 26 Oct · 04:41 UTC model run. They are not live and will have moved since.
Want the model's read each week? Subscribe for free.
Recent form
Porto
| 9 Aug | H | vs Alverca | 2–0 | W |
| 15 Aug | A | vs Rio Ave | 2–0 | W |
| 23 Aug | H | vs Arouca | 2–0 | W |
| 29 Aug | A | vs Academico Viseu | 3–0 | W |
| 4 Sept | H | vs Moreirense | 2–1 | W |
Estoril
| 7 Aug | H | vs Famalicao | 1–1 | D |
| 16 Aug | A | vs Nacional | 0–2 | L |
| 22 Aug | H | vs Rio Ave | 0–2 | L |
| 31 Aug | A | vs Benfica | 1–2 | L |
| 7 Sept | H | vs Arouca | 0–0 | D |
Head to head
No previous meetings in the Metis results archive for this competition.
Model context
| Stat | Porto (Home · 4 matches) | Estoril (Away · 4 matches) |
|---|---|---|
| BTTS rate | 50.0% | 50.0% |
| Over 2.5 rate | 50.0% | 50.0% |
| Clean sheet | 50.0% | 0.0% |
| Avg goals | 2.75 | 2.25 |
Home stats use Porto's home record; away stats use Estoril's away record this season. These are completed-match rates over the samples shown above, not model probabilities — early in a season a handful of matches produces 0% and 100% readings.