Every prediction on this site comes from one documented procedure, the PunterPick Selection Engine. It reads a licensed statistical feed, measures the shape of each fixture, and publishes the one betting market that fixture actually fits — rather than forcing every match into the same type of prediction.
Two rules sit above everything else. First: we never invent a number. If the feed has no data for a fixture, the row stays empty and is labelled NO MARKET — we do not fill the gap with an estimate. Second: nothing published here is changed after kick-off. A pick and the odds it was published at are a record, not a moving target.
A match between two attacking sides that both concede is a poor match-winner bet and a good both-teams-to-score bet. A match where one side is far stronger is the opposite. Publishing a 1X2 call on every fixture would mean publishing a weak opinion most days.
So the engine matches the market to the match. Each fixture is profiled, the profile points to a market, and only that market is published for it. This is why the same fixture does not appear on every market page — it appears on the page it belongs to.
Fixtures, results, line-ups, injuries, live scores and bookmaker odds are licensed from commercial sports-data providers under paid agreements. We do not scrape third-party sites and we never re-publish another tipster's selections as our own.
The provider also supplies its own prediction for many fixtures, as a short advice string — for example a winner, a double chance, or a goals line. Where that advice exists, it is the starting point. Where it does not, the pick is derived from the numeric data instead: scoring percentages, expected goals, and the head-to-head and form comparisons the provider publishes alongside them.
Both teams to score, correct score, first-half goal lines and corner markets are not advised by the provider at all. Those are derived entirely from the numeric feed and from bookmaker prices.
Four inputs describe the shape of a match: the probability the provider assigns to the favourite, the probability it assigns to the draw, the total goals expected across both sides, and the goals expected from the weaker side. Those four numbers decide which market the fixture is a candidate for.
A clear favourite with a low draw probability points to the match result. A match with no clear favourite but a high draw probability points to double chance. A high combined goal expectation points to over 2.5; a low one points to under 2.5. When the weaker side is still expected to score, the fixture points to both teams to score — and when it is clearly not, to both teams to score, no. A high draw probability with no favourite and a modest goal expectation points to the draw itself.
The exact thresholds for each of those are fixed in code and written down in our internal methodology contract; a threshold cannot change in one place without changing in the other.
The provider's advice is not automatically accepted. The engine scores how well the fixture fits the provider's suggested market, and how well it fits the market its own profile points to. The profile only wins when it fits clearly better — a meaningful margin, not a rounding difference. A near-tie is left with the provider.
Publication quotas exist so that one market does not swallow a whole day's card, but a quota is only ever a tie-breaker. It can decide between two equally good candidates. It can never promote a fixture into a market the fixture does not fit.
Every published pick carries the market odds it was published at. That number is there so the pick can be judged later against the price it was actually available at, not against a price that moved afterwards.
Bookmaker odds are also used as a sanity check on our own probabilities. Where our probability is materially higher than the price implies, the fixture can appear on the value bets page with the implied fair price and the size of the gap shown. Where a fixture has no price at all, no percentage is displayed — the confidence ring is left empty and the row reads no price. A probability with nothing behind it is worse than no probability.
The percentage beside a pick is the model's probability for that outcome, not a claim about how often our picks win. It is banded for readability: high, medium and low, with a distinct state for fixtures that have no price. The band is a description of confidence in that single fixture and nothing more.
On the match insight page each pick is broken down into what drove it — recent form, attack and defence ratings, expected goals, the head-to-head record, and whether the pick came from the provider's advice or from our own model. Where we used our own model because the provider gave no advice, the page says so explicitly.
We do not publish hit rates, return-on-investment figures, profit claims or staking advice. Those numbers are trivial to present favourably and almost impossible for a reader to verify, and they are the single most common way prediction sites mislead people. Our picks and their published odds are on the site; anyone who wants to keep score can keep score.
We do not accept bets, process payments, hold funds or facilitate wagering of any kind. We are an analysis site. Nothing here is betting advice, financial advice or a guarantee of any outcome.
Predictions are generated once a day, early in the morning, before that day's fixtures. Live scores and in-play events update continuously while matches are on. Standings, top scorer charts and team streaks refresh on their own slower schedules, since they change far less often.
Published predictions are kept for a short window and then removed. The site is a record of what was published before kick-off, not an archive.
If a published pick is wrong because of a data error — a fixture that did not exist, a price that was never available, a line-up that was mis-reported upstream — tell us and we will say so on the page rather than quietly deleting it. The contact address is on the contact page.
18+. Betting involves financial risk. If gambling stops being entertainment, the responsible gambling page lists where to get help.