Blog
How prediction models actually work, what betting markets really price, and how to judge anyone's tips — including ours, whose track record is public.
How to backtest a football prediction model without fooling yourself
How to backtest a football prediction model honestly: avoiding look-ahead leakage, overfitting and fantasy odds — and why no backtest replaces a live record.
ModelSupremacy and total goals: the two numbers behind a football price
Supremacy and total goals are the pair a football price is built from. How to turn them into goal expectancies, a scoreline grid and every market.
TransparencyWhy football stats differ between sites (and what it does to predictions)
Two sites, one match, different numbers. Why football stats differ between sites — collection, definitions, revisions — and what it does to a prediction model.
ModelExpected points (xPts): the justice table and its limits
Expected points turns chance quality into league position. It explains the past well and predicts the future badly — and the two versions of xPts are not the same metric.
ModelRed cards in football predictions: what a sending-off really costs
Red cards in football predictions, quantified: what a sending-off does to goal expectancy, why the minute matters more than the card, and how to judge it.
TransparencyHow our football Bet of the Day is picked
Our Bet of the Day is picked by the model, not a hunch: its single most confident call of the day at a price worth taking, free, with every past pick graded in public.
Betting 101Multi goals betting explained: how to price a 2-3 goals band
Multi goals betting explained: how to price a 2-3 goals band from a goal distribution, why multiplying two half-goal lines fails, and where the margin hides.
TransparencyThe ranked probability score in football, and when it beats Brier
The ranked probability score in football, explained: the cumulative formula, why a draw sits between two wins, and when it beats a Brier score.
LeaguesThe 40-point rule: does 40 points really keep you up?
The 40-point rule is football's most durable number. Testing it against how relegation actually works — and why survival is a probability, not a target.
LeaguesHow many points do you need to avoid relegation?
How many points to avoid relegation is the wrong question — the safety line is a distribution set by other clubs. Here is how to read it as a probability.
TransparencyFixed match scams: how they actually work
Match-fixing is real. A stranger selling you access to it is not. The economics of why, the mechanics of the con, and the checks that survive contact with a good sales pitch.
ModelHead-to-head records in football predictions: signal or noise?
Head-to-head records in football predictions, checked against the math: why five past meetings rarely beat five seasons of data — and when H2H does inform.
Betting 101The biggest upsets in our data, and why they aren't surprising
The longest-priced winners across 16,628 matches — and the calibration table showing that longshots come in roughly as often as they should, while costing far more than they're worth.
Betting 101Corner betting predictions: the market we don't price, and why
Corner betting predictions, priced honestly: how a corner total is modelled, why plain Poisson gets the spread wrong, and why we publish no corner numbers.
TransparencyAre AI Football Predictions Real, or Just Statistics With a New Label?
Are AI football predictions real? Most 'AI-powered' tips sites run the same statistics prediction sites always have. Here's how to tell the difference.
Betting 101Asian total goals explained: the shortcut that works on half the lines
Asian total goals explained: how a quarter line splits your stake, and why averaging the two neighbouring prices is exact on Over 2.25 and 4.6% too generous on 2.75.
TransparencyWhy football prediction models disagree, and how to read the gap
Why football prediction models disagree on the same match, what the size of the gap actually tells you, and which model deserves the benefit of the doubt.
LeaguesChampions League prediction model explained: why it isn't the league model
A champions league prediction model can't reuse a domestic one. Shared-scale ratings, cross-league starting points and a worked example show the problem any model has to solve.
TransparencyHow to spot a fake football tipster: five tests you can run
How to spot a fake football tipster with arithmetic instead of instinct: five tests on win-rate claims, advised odds, settlement rules and sample size.
TransparencyStatistical significance in a betting record: the test and its limits
How to test statistical significance in a betting record: the right null hypothesis, a worked z-test, and why a p-value under 0.05 still isn't proof.
LeaguesChampions League league phase predictions: 36 teams, one table, unequal fixtures
Champions League league phase predictions can't use normal table logic — each club plays 8 of 35 rivals. How strength of schedule and simulation fix it.
Betting 101How to remove the vig from football odds: three methods compared
How to remove the vig from football odds: the proportional method, why it distorts a three-way 1X2 book, and two better alternatives with worked numbers.
TransparencySurvivorship bias in betting: why a winning tipster always exists
Survivorship bias in betting, with the arithmetic: how pure chance manufactures a flawless tipster record, and the record structure that can't be faked.