Norwich
PortsmouthThis call was made before kick-off.
Most likely: Norwich win
Oddbert gives Norwich a 49% chance of winning.
In 100 matches like this, Norwich would win about 49. In the other 51 or so, Norwich doesn't win.
Dot chart of 100 matches like this: Norwich win 49, Draw 27, Portsmouth win 24.
Each dot is one match out of 100 like this.
Guess the result — no money, no points. After the match you'll see your guess next to Oddbert's chance and the result.
Your guesses are saved in this browser only.
Our model vs market
Our blended model differs from the price here. This is our own view, not a validated edge — we show it openly, but we don't claim it beats the market until it has done so out-of-time.
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 17 Oct 2026
Guess the result — no money, no points. After the match you'll see your guess next to Oddbert's chance and the result.
Your guesses are saved in this browser only.
In this Championship fixture, the model assigns Norwich a 49% probability of securing a win, while Portsmouth holds a 24% chance. The prospect of a draw is calculated at 27%. These figures suggest that while the model leans toward Norwich, the outcome remains open. When examining the underlying factors, the picture is nuanced. The model finds support for its lean in the Pi-rating edge, which favors the home side. However, this is partially offset by the "what’s at stake" variable regarding home advantage, as well as Norwich’s recent defensive expected goals (xG) form, both of which work against the home side's outlook. Relative to the broader market, the model’s valuation of Norwich sits slightly below the current market price, suggesting a divergence in how these teams are being priced versus the model's output. Recent form highlights distinct trajectories. Norwich enters this match having recorded four consecutive losses following a victory, indicating a challenging period for the side. In contrast, Portsmouth’s recent form shows more volatility, with a record of two wins, a loss, and two draws across their last five outings. Historical data between the two clubs offers little clarity, as previous meetings have been roughly even. Injury information was not available when this was written.
The AI writes the prose. It never produces or adjusts a probability — those come only from our forecast.
Odds include the bookmaker's margin.
The highlighted price is the highest among the bookmakers with a Danish licence.
Words explained:
| Bookmaker | Norwichpays 1% more than the typical book | Drawpays 4% more than the typical book | Portsmouthpays 13% more than the typical book |
|---|---|---|---|
| Bet365 | 1.80 | 3.80 | 4.10 |
| Marathonbet | 1.81best | 3.75 | 3.90 |
Bookmaker names shown for reference only. No affiliate links.Bookmakers' names are here for reference only. We don't link to them.
Bookmaker odds are turned off. You can turn them back on under Display at the bottom of the page.
Oddbert gave Norwich 49% — the match ended 0–1.
The most likely result didn't happen this time.
↑ stronger · = even · ↓ weaker opponent
↑ stronger · = even · ↓ weaker opponent
Absence data is not available for this match.
Absence data is not available for this match.
Recent form — context only, not a tip.
How the model sees this match — the drivers and, after full-time, how the prediction scored.
The model assigns a 49% probability to a Norwich victory, with a 27% chance of a draw and a 24% probability of a Portsmouth win. This lean toward Norwich is primarily supported by the model’s calculation of a Pi-rating edge, though this is tempered by concerns regarding the team's recent home defensive xG form and the inherent challenges of playing at home in this specific context. While Norwich has struggled in their recent matches with four losses in their last five, Portsmouth arrives with a more varied recent record of two wins, two draws, and a loss. Injury information was not available when this was written.
The AI writes the prose. It never produces or adjusts a probability — those come only from our forecast.
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.
Words explained: