Model output, not advice. These are probabilities from a
statistical model, published for transparency about how it performs. They are
not tips and not financial advice. In backtests this model does not
reliably beat closing prices, which is the only benchmark that matters, so
expect selections here to lose money over time. 18+. Gambling is addictive; if
it stops being a modelling exercise, stop.
MTN8 MTN8 (South Africa) · 2 fixtures across 2 days
Best value on this date
Stake is blank unless a selection clears every gate: positive expected value, at least 5 percentage points of edge over the de-vigged line, and not more than 25 (a disagreement that large is usually the model missing something, not an opportunity). Most rows will be blank most days. Selections marked longshot are below 10% — their EV figure divides by a very small number and should not be trusted. thin data means one side has too few matches in the model's history for its rating to mean anything; the huge edge shown is the model's ignorance, not the market's mistake.
Sekhukhune United HOME
v Orlando Pirates AWAY
13:00 ·
MTN8 · expected goals
Sekhukhune United 0.83 – 1.43 Orlando Pirates
Sekhukhune United 19%
· draw 26%
· Orlando Pirates 56%
Sekhukhune Un… or draw
44%
draw or Orlando Pirat…
81%
Sekhukhune Un… clean sheet
24%
Orlando Pirat… clean sheet
44%
Likeliest scores: 0–1 15% · 1–1 13% · 0–0 11% · 0–2 11%
Half-time markets
| Sekhukhune United | Draw | Orlando Pirates |
|---|
| Model | Book | Edge | Model | Book | Edge | Model | Book | Edge |
|---|
| 1st half | 18.3% | — | — | 45.2% | — | — | 36.4% | — | — |
| 2nd half | 20.0% | — | — | 39.0% | — | — | 40.9% | — | — |
Correlated combinations
- Sekhukhune Un… win + Sekhukhune Un… clean sheet — 13% (fair 7.69); naive multiplication would say 5%, off by +157%
- BTTS Yes + Over 2.5 — 31% (fair 3.28); naive multiplication would say 17%, off by +79%
- Orlando Pirat… win + Orlando Pirat… clean sheet — 33% (fair 3.04); naive multiplication would say 22%, off by +48%
- Draw + Under 2.5 — 24% (fair 4.24); naive multiplication would say 17%, off by +40%
Best value on this date
Stake is blank unless a selection clears every gate: positive expected value, at least 5 percentage points of edge over the de-vigged line, and not more than 25 (a disagreement that large is usually the model missing something, not an opportunity). Most rows will be blank most days. Selections marked longshot are below 10% — their EV figure divides by a very small number and should not be trusted. thin data means one side has too few matches in the model's history for its rating to mean anything; the huge edge shown is the model's ignorance, not the market's mistake.
Mamelodi Sundowns HOME
v Golden Arrows AWAY
13:00 ·
MTN8 · expected goals
Mamelodi Sundowns 2.36 – 0.70 Golden Arrows
Mamelodi Sundowns 71%
· draw 18%
· Golden Arrows 11%
Mamelodi Sund… or draw
89%
Mamelodi Sund… clean sheet
50%
Golden Arrows clean sheet
9%
Likeliest scores: 2–0 13% · 1–0 11% · 3–0 10% · 2–1 9%
Half-time markets
| Mamelodi Sundowns | Draw | Golden Arrows |
|---|
| Model | Book | Edge | Model | Book | Edge | Model | Book | Edge |
|---|
| 1st half | 54.6% | — | — | 34.3% | — | — | 11.1% | — | — |
| 2nd half | 60.6% | — | — | 28.1% | — | — | 11.3% | — | — |
Correlated combinations
- Draw + Under 2.5 — 13% (fair 7.73); naive multiplication would say 7%, off by +88%
- BTTS No + Under 2.5 — 33% (fair 3.03); naive multiplication would say 22%, off by +49%
- BTTS Yes + Over 2.5 — 38% (fair 2.64); naive multiplication would say 27%, off by +40%
- draw or Golden Arrows + Under 3.5 — 20% (fair 4.98); naive multiplication would say 16%, off by +23%