Milford FC v Durban City — Prediction, Odds & Stats
Sunday 20 September 2026 · RSA-Premiership · 2627
RSA-Premiership
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
- 0-0 21.6%
- 1-1 15.4%
- 1-0 14.6%
- 0-1 12.3%
- 2-0 7.6%
Goals
| Over 2.5 | 23.0% | Under 2.5 | 77.0% |
| BTTS yes | 33.8% | BTTS no | 66.2% |
| Milford FC 1+ | 58.8% | Milford FC 2+ | 22.3% |
| Durban City 1+ | 53.4% | Durban City 2+ | 17.8% |
Expected goals 0.89 – 0.76. Every market above is read off one scoreline distribution.
Footing
Positive factors
- Milford FC carry the stronger rating, 1517 Elo against 1480.
Risk factors
- Data quality is 45/100, so this price rests on less than the model would like.
- Milford FC have only 5 matches on record.
Why the model thinks this
The price
The draw is the single most likely outcome at 39.4%, with Milford FC at 33.8% and Durban City at 26.8%. Expected goals from the ensemble are 0.89 for Milford FC and 0.76 for Durban City.
Why Milford FC
Milford FC carry the stronger rating, 1517 Elo against 1480.
Why the draw is live
The draw sits at 39.4%. A combined 1.65 expected goals is a low-scoring profile, and low totals mean more level finishes. The sides are closely matched on expected goals, 0.89 to 0.76. Draws run at 31% in this competition.
Why Durban City can win
Nothing in the data singles out Durban City.
Key players
No player-level data for this fixture; the leagues with lineups are the big five.
Availability
No lineup on record for Milford FC, so availability is unknown. No lineup on record for Durban City, so availability is unknown.
The matchup, as far as the data reaches
Milford FC: 52% possession, 12.8 shots a match, 11.0 faced, 0.30 xG a match from set pieces. Durban City: 59% possession, 14.6 shots a match, 10.6 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 ·
A draw is the model's most likely outcome at 39.4%. The likeliest scoreline is 0-0 at 21.6%. Confidence 62/100, data quality 45/100. 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 | 0.89–0.76 | 0% | 0% | 0% | |
| dc-xg | 0.63–0.55 | 0-0 33% | 12% | 22% |
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.