Pick two teams and see who's likely to win, powered by a
Dixon-Coles model fitted on a century of international football.
VS
win
Draw
win
Expected goals
–
average goals per match for each side
Most likely scorelines
Victory margin
exact scorelines split a favourite's dominance into many small slices; this view groups them back together
Betting view: fair odds
fair odds = the break-even price for each market. A real bet only has value
if a bookmaker offers higher odds than shown here. Probabilities refer to the 90-minute
result, are estimates with no lineup/injury knowledge, and are not betting advice. If you
bet, bet responsibly.
How this predictor works
Under the hood this site runs a Dixon-Coles model: a pair of Poisson
goal models, one per team, fitted on international results from 1990 to today.
Every past match shapes each team's attack and defence rating, but not equally:
recent games and big tournaments count far more than ancient friendlies, thanks
to an exponential time decay (a result loses half its influence every four years)
and per-competition weights (a World Cup match matters roughly twice as much as a
friendly). From those ratings the model computes how many goals each side is
expected to score, builds a probability grid over every possible scoreline
(with the Dixon-Coles correction that fixes the plain Poisson model's blind spot
on low-scoring draws) and then runs thousands of Monte-Carlo simulations to
produce the win/draw/loss percentages and most likely scorelines you see. For
teams with little recent data the estimate is blended with an Elo-rating prior,
so one obscure fixture can't produce a wild prediction. Everything runs locally
in your browser, no server involved.
What the tags mean
Expected goals (xG home / xG away)
The model's average goals per match for each side: if this matchup were
played many times, this is what each team would score on average. A 1.8–0.9
reading is not a score prediction; it says team 1 creates about twice
team 2's scoring output.
Use xG data
Switches to team strengths fitted with StatsBomb expected-goals numbers
blended into the actual results. xG measures the quality of chances created
rather than just goals scored, which is often a better signal of how good a
team really is than the final scoreline.
When to use which: turn xG on when you want the fairest
read on which team is genuinely stronger, since it filters out finishing
luck. Turn it off after pressing Refit latest: the refit
updates only the standard model, so with xG off your prediction includes
the very newest results.
⟳ Refit latest
Downloads the newest international results (~4 MB) and re-fits the entire
model right in your browser, so matches played since this site was published
are taken into account. Takes a few seconds; applies to the standard model
(the xG bundle keeps its original fit).
Dixon-Coles vs Skellam
Dixon-Coles evaluates the full scoreline matrix with the low-score
correction, the accurate choice. Skellam approximates using only the
distribution of the goal difference; slightly faster, slightly cruder.
Most likely scorelines
Exact probabilities computed from the model's full scoreline matrix,
not random samples, so the same matchup with the same settings always
shows the same numbers. In football the top scorelines are often nearly
tied at around 10% each; no single final score is ever truly "likely".
Betting view: fair odds
Each market's model probability converted to decimal odds (1 ÷
probability), the break-even price. Bookmakers add a margin, so their
odds on "safe" favourites are usually below fair value; a bet is only
mathematically good when their offered odds are higher than the fair odds
here. Markets settle on the 90-minute result: in knockout games a win
bet loses if the team only wins in extra time. The model knows nothing about
lineups or injuries. Not betting advice.
Victory margin
The same probabilities regrouped by the final gap in goals instead of the
exact score: "how big will the difference be?" rather than "exactly
which scoreline?". Like dice: rolling exactly 4+3 is rare, but a total of 7
is the most common sum, because many combinations produce it. Likewise a
team's "win by 2+" bundles 2-0, 3-0, 3-1, 4-1… into one group that can
be the most likely outcome even though each exact score looks small alone.
Works for any matchup; between equals, "draw" and "by 1" simply become
the big bars.
Team 1 at home
Applies the fitted home-advantage boost (roughly 25% more goals) to
team 1. Leave it off for a neutral venue, as in most World Cup matches.
♥ Support the project
This predictor is free, open and runs entirely in your browser. If it made
your World Cup a little more fun, you can chip in to keep it running and
improving. Any amount is hugely appreciated!