NEC Nijmegen
Levski SofiaMost likelyNEC Nijmegen win · 49%
Best price1.93 Betano
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 this upcoming UEFA Europa League fixture, NEC Nijmegen faces Levski Sofia in a matchup where the model assigns NEC Nijmegen a 49% probability of victory. A draw is calculated at 27%, while Levski Sofia’s probability of securing a win stands at 24%. Given these figures, the model maintains a lean toward the home side, though it places the valuation of NEC Nijmegen slightly below current market pricing. Several tactical factors influence this outlook. The model’s assessment is buoyed by Levski Sofia’s recent defensive expected goals (xG) form when playing away from home, which provides support for the NEC leaning. Conversely, the model identifies potential headwinds for the hosts: specifically, the pressure associated with what is at stake for NEC on home soil, alongside concerns regarding Levski Sofia’s attacking xG form when playing away, which also pulls against the model’s overall projection. Recent form offers a contrast in momentum between the two clubs. NEC Nijmegen arrives at this encounter with a sequence of draw, draw, loss, loss, draw, indicating a period of inconsistent results. In comparison, Levski Sofia enters with a run of loss, loss, draw, win, win, showing a more positive recent trend. Neither side has reported injuries ahead of the match, though these reports do not account for potential squad rotation or decisions to rest starters, as confirmed lineups have yet to be determined. As these two clubs prepare for what will be their first-ever meeting, the model’s data suggests that while the home side is positioned as the likeliest outcome, the competing factors of defensive and offensive metrics—paired with the nuances of market pricing—create a complex landscape for this Europa League tie.
The AI writes the prose. It never produces or adjusts a probability — those come only from the model.
| Bookmaker | NEC Nijmegenpays 4% more than the typical book | Drawpays 4% more than the typical book | Levski Sofiapays 3% more than the typical book |
|---|---|---|---|
| Bet365 | 1.85 | 3.70 | 3.90 |
| Betano | 1.93best | 3.90best | 4.00 |
| Betfair | 1.85 | 3.75 | 4.00best |
| Marathonbet | 1.88 | 3.82 | 3.96 |
Bookmaker names shown for reference only. No affiliate links.
Two ways to size a hypothetical stake on the model's call — NEC Nijmegen at 1.93 (Betano).
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 assigns a 49% probability to a victory for NEC Nijmegen, compared to 27% for a draw and 24% for a Levski Sofia win, placing it slightly below current market pricing for the home side. This lean toward NEC Nijmegen is largely driven by favorable away defensive expected goals (xG) form, though the model notes that the high stakes for the home team and Levski Sofia's own attacking xG form create counter-pressures. While neither team has reported any injuries, it is important to note that lineups remain unconfirmed, meaning potential squad rotation or player rest is not factored into these figures. These teams have no previous head-to-head history to draw upon, leaving recent results—which include a string of draws for NEC Nijmegen and a mixed sequence of wins and losses for Levski Sofia—as the primary contextual markers.
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.