Celje
Omonia NicosiaMost likelyCelje win · 36%
Best price2.70 Bet365
Market-anchored: the market's vig-free price (1 sharp book) + model lean (max ±3 pp)
These are calibrated probabilities. See how closely they've matched real outcomes
Prediction as of 15 Oct 2026
In the upcoming UEFA Europa League fixture, Celje and Omonia Nicosia face off in a matchup that our model views as a tightly contested, open encounter. With neither side establishing a clear dominance in the projections, the probabilities paint a picture of a toss-up: Celje is modeled at 36%, Omonia Nicosia at 34%, and a draw at 30%. These figures suggest that the outcome is statistically wide open, as the model offers only a marginal lean toward the home side. Several competing factors contribute to this assessment. Celje enters with a mixed recent form—loss, loss, draw, win, loss—though the model finds their home performance to be a relative support point for the slight lean they hold. Conversely, the model identifies Celje’s defensive expected goals (xG) form at home and the situational pressure of what is at stake for them as factors working against their probability. Omonia Nicosia presents a more positive recent run, having posted a record of win, win, loss, win, draw across their last five matches. Despite this stronger recent trajectory, the model’s overall output remains aligned with the broader market pricing regarding Celje’s standing in the match. Heading into this first-ever meeting between the two clubs, squad availability remains a key variable. There are no reported injuries for either side; however, as confirmed lineups have not yet been announced, these reports do not imply either team is at full strength. Both managers retain the flexibility to implement squad rotation or rest starters ahead of kickoff, a factor not currently captured in these probabilities. With the teams so closely matched by the numbers, the game is set up to be decided by fine margins on the pitch.
The AI writes the prose. It never produces or adjusts a probability — those come only from the model.
| Bookmaker | Celjepays 3% more than the typical book | Drawpays 3% more than the typical book | Omonia Nicosiapays 3% more than the typical book |
|---|---|---|---|
| Bet365 | 2.70best | 3.25 | 2.62 |
| Betano | 2.65 | 3.40 | 2.67 |
| Betfair | 2.63 | 3.50best | 2.63 |
| Marathonbet | 2.62 | 3.38 | 2.71best |
Bookmaker names shown for reference only. No affiliate links.
Two ways to size a hypothetical stake on the model's call — Celje at 2.70 (Bet365).
Stays in your browser — never sent to us.
Flat 1% of bankroll — the same rule as our public AI bankroll simulation.
Quarter-Kelly at the best listed price, with a hard 5%-of-bankroll cap.
Hypothetical sizing in currency-neutral units, not betting advice. Predictions are probabilities, not guarantees. 18+.
↑ stronger · = even · ↓ weaker opponent
↑ stronger · = even · ↓ weaker opponent
No reported absences.
No reported absences.
No previous meetings on record.
Recent form — context only, not a tip.
No line movement recorded yet
No line movement recorded yet
No line movement recorded yet
How the model sees this match — the drivers and, after full-time, how the prediction scored.
The model views this UEFA Europa League clash between Celje and Omonia Nicosia as a tight, open contest, assigning a 36% probability to a Celje victory, 34% to an Omonia Nicosia win, and 30% to a draw. While the model leans slightly toward Celje, driven by the team's recent home form, this positive indicator is balanced against concerns regarding their defensive expected goals metrics and the pressure associated with what is at stake for the home side. The probabilities are broadly in line with current market pricing, reflecting the lack of direct head-to-head history and the unpredictable nature of this match-up. With no injuries reported for either side, the potential for squad rotation remains an unknown variable that the model cannot account for at this stage.
The AI writes the prose. It never produces or adjusts a probability — those come only from the model.
How we make these predictionsThe driver chips attribute the gradient-boosted component of an ensemble whose headline is additionally anchored to the market where a consensus exists — they explain that part of the number, not all of it.