Why Correct Score Models Favour 1-1: Poisson Maths Made Simple

You’ll sometimes see it claimed that 1-1 is “the most common scoreline in football,” usually without much explanation of why. The underlying reason comes from a piece of statistics called the Poisson distribution, and it’s genuinely useful to understand even if you never touch a calculator again after reading this.

What a Poisson Model Actually Does

A Poisson distribution describes the probability of a certain number of independent events happening in a fixed window, given an average rate. Goals in football fit this reasonably well as a simplifying assumption: each team has an average expected goals figure for a given match — based on attacking quality, opponent defensive quality, and home advantage — and the model treats actual goals scored as random occurrences around that average.

Crucially, a Poisson model doesn’t predict an exact score. It generates a probability for every possible scoreline, and the scoreline with the single highest probability is simply the most likely outcome among many, not a “prediction” in the sense of a confident forecast.

A Worked Illustrative Example

Take a hypothetical match where, purely for illustration, the home side has an expected goals average of 1.55 and the away side 1.15 — representative, rough, illustrative figures rather than any specific real fixture. Using the Poisson formula for each team’s goal count and multiplying the two independent probabilities together for every scoreline combination produces results like these:

These figures were calculated directly from the Poisson formula using the illustrative 1.55/1.15 expected-goals inputs above, so they’re mathematically consistent with that specific starting assumption — change the expected-goals inputs for a different hypothetical match and every number shifts accordingly.

Why 1-1 Comes Out on Top Here

Notice that 1-1 edges out even 1-0, which might feel counterintuitive at first — surely a home win should be more likely than a draw if the home side is the stronger team in this scenario? The reason is that 1-0 is only one specific combination (home scores exactly once, away scores exactly zero), while 1-1 benefits from both teams’ expected-goals rates overlapping at a moderate, individually quite probable number. When both teams have expected-goals averages in a broadly similar low-to-moderate range — as most competitive matches do — the combination where both teams score exactly once tends to edge out any single 1-0 or 2-0 combination specifically because “both score once” is a comparatively likely event for each side individually, and multiplying two moderately likely individual events together at these goal levels compounds in 1-1’s favour.

Why This Isn’t a Prediction

It’s worth being very clear about what this maths does and doesn’t tell you. Even in the table above, 1-1 at roughly 12% means the model still expects that specific scoreline to be wrong around 88% of the time. A Poisson model is a way of organising uncertainty sensibly, not a method for eliminating it. Real matches also violate some of the model’s simplifying assumptions — goals aren’t perfectly independent events (a team leading 1-0 often adjusts its approach, changing the probability of further goals), and expected-goals inputs themselves are estimates, not known facts.

Practical Takeaways for Coupon Players

• 1-1 being statistically favoured among specific scorelines is a real, calculable pattern, not folklore — but it’s a modest lean, not a strong one
• No correct-score model, however carefully built, should be read as a guaranteed or even highly confident forecast
• The model is most useful for comparing relative likelihoods between scorelines, not for treating any single output as the “right” answer
• Always treat expected-goals inputs as estimates — garbage in, garbage out applies as much to football models as anywhere else

Understanding the mechanics behind a claim like “1-1 is the most common scoreline” is far more useful than just repeating it, because it tells you when the claim is likely to hold (fairly even, moderate-scoring matchups) and when it’s likely to break down (a heavy mismatch where one side’s expected-goals rate is far higher than the other’s, shifting the most probable scoreline elsewhere entirely).

What Happens When the Expected-Goals Gap Widens

To illustrate the breakdown point directly, consider a second hypothetical scenario where the home side’s expected-goals average is a much higher 2.40 against an away side at 0.70 — again, purely illustrative inputs representing a genuine quality mismatch rather than a real fixture. Running the same Poisson calculation shifts the single most probable scoreline toward a clear home win, typically 2-0 or 2-1 depending on the exact inputs, with 1-1 dropping meaningfully down the probability ranking. This is the practical lesson worth taking away: the “1-1 is most common” pattern is specifically a feature of closely matched, moderate-scoring fixtures, not a universal football truth that applies regardless of the two teams involved.

Why Bookmakers and Modellers Still Use Poisson as a Starting Point

Despite its simplifying assumptions, the Poisson approach remains a common starting point in football modelling because it’s transparent, easy to recalculate for any pair of expected-goals inputs, and reasonably good at capturing the broad shape of how goals are distributed across a season of matches, even if it misses some of the finer in-game dynamics. More sophisticated models build on this Poisson foundation by adjusting for factors like a team’s tendency to sit back after taking an early lead, or correlations between the two teams’ goal-scoring that a purely independent Poisson calculation doesn’t capture on its own. For a coupon player without access to that level of modelling, understanding the basic Poisson logic still gives you a genuinely useful mental framework for reasoning about scoreline likelihood, even without running the actual calculation yourself every week.

A Closing Thought on “Guaranteed” Scorelines

Whenever you see a site or tipster describe a specific scoreline as a safe, reliable, or near-guaranteed outcome, the Poisson maths above is a useful reality check: even the single most probable scoreline in a well-built model typically sits somewhere between 10% and 15% likelihood in a reasonably competitive match, meaning it’s wrong considerably more often than it’s right. That’s not a flaw in the method — it’s simply an honest reflection of how much genuine uncertainty exists in a 90-minute football match, whatever model you’re using to think about it.

Responsible play reminder: statistical modelling, however carefully done, never produces a guaranteed result. Set a budget you’re comfortable with before playing, treat the pools as entertainment rather than income, and remember this content is intended for readers aged 18 and over.