UD Songo v Petro de Luanda — Prediction, Odds & Stats
Sunday 6 September 2026 · CAF-Champions League · 2627
CAF Champions League
results-only Prediction generated
AI prediction
ai-blend v1.0 dailyRaw model output; no calibration record for this fixture's bands yet.
Top 5 scorelines
- 1-0 12.9%
- 1-1 12.6%
- 2-0 9.3%
- 2-1 9.0%
- 0-0 8.9%
Goals
| Over 2.5 | 43.4% | Under 2.5 | 56.6% |
| BTTS yes | 47.5% | BTTS no | 52.5% |
| UD Songo 1+ | 76.3% | UD Songo 2+ | 42.2% |
| Petro de Luanda 1+ | 62.3% | Petro de Luanda 2+ | 25.5% |
Expected goals 1.44 – 0.98. Every market above is read off one scoreline distribution.
Footing
Positive factors
- At home UD Songo average 1.35 xG a match.
Risk factors
- Data quality is 0/100, so this price rests on less than the model would like.
- UD Songo have only 0 matches on record.
- Petro de Luanda have only 6 matches on record.
Why the model thinks this
The price
UD Songo have an estimated 47.8% win probability, against 26.6% for the draw and 25.6% for Petro de Luanda. Expected goals from the ensemble are 1.44 for UD Songo and 0.98 for Petro de Luanda.
Why UD Songo
At home UD Songo average 1.35 xG a match.
Why the draw is live
The draw sits at 26.6%. Draws run at 33% in this competition.
Why Petro de Luanda can win
They have had 30 days' rest to UD Songo's 14.
Key players
No player-level data for this fixture; the leagues with lineups are the big five.
Availability
No lineup on record for UD Songo, so availability is unknown. No lineup on record for Petro de Luanda, so availability is unknown.
The matchup, as far as the data reaches
UD Songo: 50% possession, 12.0 shots a match, 12.0 faced, 0.30 xG a match from set pieces. Petro de Luanda: 50% possession, 12.0 shots a match, 12.0 faced, 0.30 xG a match from set pieces.
Inputs last refreshed: matches 2026-09-06 07:42 · team_stats 2026-09-06 06:08 · availability 2026-09-06 07:53 · prediction 2026-09-05 18:39 ·
UD Songo are the model's most likely outcome at 47.8%. The likeliest scoreline is 1-0 at 12.9%. Confidence 0/100, data quality 0/100. These are probabilities, not certainties: the less likely outcome happens as often as its number says.
Written from the numbers the model saw, not by a language model; nothing here is a statistic the snapshot does not hold. How predictions work.
Was this pick made in advance?
-oos is out of sample: it was fitted only on matches
played before this one, so its pick is a genuine forecast rather than hindsight.
Anything without that suffix was fitted on all available data.What the model said
| Model | Home / Draw / Away | Expected goals | Likeliest score | O2.5 | BTTS |
|---|---|---|---|---|---|
| ai-blend | 1.44–0.98 | 0% | 0% | 0% |
A model whose name ends -oos was produced by the walk-forward backtest:
it was fitted only on matches played before this one, so the pick is genuinely out of sample.