AI football betting prompts built around xG and the fair price
Football is the hardest sport to prompt well: three Ergebnisse, low scoring, and the most efficient Markt in betting. A prompt that ignores the Unentschieden or trusts a 4-0 result over the xG behind it will lose slowly and confidently.
What a football prompt has to get right
The first job of a football prompt is arithmetic, not opinion: strip the Buchmachermarge out of the 1X2 prices so the model starts from a fair baseline instead of an inflated one. Everything after that is an adjustment — form measured in xG rather than Punkte, the home-away split of each side, who is missing, and how many days of rest each team had.
The second job is to keep the Unentschieden honest. Roughly a quarter of Spiele in the big European leagues end level, and models left to their own instincts systematically under-price that. Both prompts below force a three-number Wahrscheinlichkeit set that sums to 100%, so an under-weighted Unentschieden becomes visible immediately instead of hiding inside a confident "home Sieg".
The third job is scale. Football is by far the largest slate on the board — well over a thousand fixtures land in a fortnight — so a prompt that only works when you have read the team news is a prompt you will use twice. Both versions below are written to run on whatever you can paste in from a Spiel page, and to say so when that is not enough.
De-vig before you predict
Convert 1X2 Quoten to implied probabilities, remove the overround, and treat the result as the baseline. A prompt that starts from raw Quoten is starting from a number that already sums to more than 100%.
xG over results
Five-Spiel samples of Tore are almost noise. xG for and against, shot volume and shot quality tell you whether a run of Siege is real. Value lives where the table lags the underlying performance.
Heim-away split, not season averages
Many sides are a different team away from home — deeper block, fewer shots, more draws. Feed the split explicitly, otherwise the model averages the two into something that describes neither.
Rotation, injuries and congestion
A midweek European tie three days earlier, a suspended centre-back, a keeper change. These move the price more than most narratives, and they are the factors a model cannot guess — you have to supply them.
Football prompts v1 and v2 — and how they differ
The same model, two instruction sets, two different betting personalities. Run both on the same Spiele; that comparison is the only thing that settles the argument.
| Version | Focus | Style | Best for |
|---|---|---|---|
| v1 | Fair 1X2 baseline, then small adjustments | Disciplined | 1X2, consistency |
| v2 | Shot quality and Tore Märkte | Tors-hunting | Totals and BTTS value |
You are a disciplined football betting analyst. Spiel: {home} vs {away}, {league}, {date}. Markt 1X2: {Quoten}.
Step 1: convert the 1X2 Quoten to implied probabilities and remove the Buchmachermarge to get a fair baseline.
Step 2: adjust that baseline only for verifiable factors — form measured in xG for/against (last 5), confirmed injuries and suspensions, home form for the home side and away form for the away side, days of rest and travel. Do not adjust for narratives or motivation.
Keep the Unentschieden honest: it is roughly 25% in most top leagues.
Output exactly:
1) Heim / Unentschieden / away probabilities summing to 100%
2) Main Tipp + Sicherheit 1-10
3) Best value Markt (1X2 / Über-Unter 2.5 / BTTS) and the reason
4) Most likely correct Ergebnis
5) One-Linie reasoning
If your fair price Spiele the offered price, answer "no bet".
You are an attacking-metrics football analyst. For {home} vs {away} ({league}, {date}):
Base your read on xG for and against, shot volume and shot quality, set-piece threat and how high each defensive Linie plays — not on results. Lean into Tore Märkte when both attacks create real chances, and away from them when either side suppresses shot quality.
Compare every conclusion with the posted Linie {Quoten} and flag where the Markt disagrees with the underlying numbers.
Output exactly:
1) Predicted Ergebnis
2) Über/Unter Tipp with the Linie you are using
3) BTTS ja/no
4) 1X2 Tipp + Sicherheit 1-10
5) The single decisive factor
If the xG samples are too small to separate the sides, say so and answer "no bet".
Placeholders in braces are filled automatically when you run a prompt from a Spiel in the AI Lab. Pasting into your own chat window works too — just replace them by hand.
What to feed the model, and what a usable answer looks like
Feed it this
- League, matchweek and kick-off date — plus cup Kontext if the Spiel is a dead rubber.
- Last five Spiele per side with xG for and against, not just scorelines.
- Heim form for the home team, away form for the away team — separately.
- Confirmed absences: injuries, suspensions, and any keeper or centre-back change.
- Days of rest since the last Spiel and travel distance.
- The Linie: 1X2, Über-Unter 2.5 and BTTS. Weather too, if it is extreme.
Good output has
- Three probabilities for home / Unentschieden / away summing to exactly 100%.
- A main Tipp plus Sicherheit 1-10, with a low Ergebnis allowed.
- The best value Markt of the three (1X2, Über-Unter, BTTS) and why.
- A most-likely correct Ergebnis, which exposes an incoherent Wahrscheinlichkeit set fast.
- One decisive factor in one Linie — no paragraph of hedging.
- A clear "no bet" when the fair price and the offered price stimmen überein.
Where football prompts usually go wrong
- Unter-weighting the Unentschieden (it is around 25% in most top leagues).
- Reading one 4-0 as a step change instead of variance.
- Motivation narratives ("they need the Sieg") replacing data.
- Totals Tipps that ignore how each side actually creates shots.
Quoten, model Kontext and Markt drift for each fixture are on the football Spiele with Quoten and AI Tipps board, so most of the input list above can be copied straight from the Spiel page.
Prompting the three Märkte football actually offers
A prompt that only answers "who Siege" throws away most of a football card. The three liquid Märkte reward different reasoning, and asking for all three in one answer is also the cheapest coherence check you have: a 1X2 read, a totals read and a correct Ergebnis that contradict each other tell you the model is guessing.
Three-way, Unentschieden included
Demand three probabilities that sum to 100% and compare each with the de-vigged price. The Unentschieden is the honesty test — a model that prices it under 20% in a tight league Spiel is not reasoning, it is picking a Favorit.
Totals need shot creation, not results
Über-Unter is a question about how each side generates and concedes chances: shot volume, shot quality, set-piece threat, defensive Linie height. Two Teams that both create little produce unders regardless of how attacking their reputations are.
Beide Teams treffen
BTTS is close to two independent scoring questions, so ask for each side's chance of scoring separately before the ja/no. It is also where a weak keeper or a missing centre-back moves the honest number most.
Handicaps and correct Ergebnis
Ask for a most likely correct Ergebnis even when you are not betting it: it exposes an incoherent Wahrscheinlichkeit set instantly. If the model says 55% home Sieg and predicts 1-1, one of those two numbers is wrong.
Measure both versions before you trust either
Store both versions
Save v1 and v2 as separate prompts in the AI Lab so every run is attributed to a version instead of blurring together.
Run them on the same Spiele
Tipp fixtures from the football board and lock both forecasts before start. Same slate, same information, no hindsight.
Judge on ROI, not hit-rate
A value prompt taking underdogs will always look worse on hit-rate and can still be the profitable one. Settlement and scoring are automatic once the Spiel finishes.
The AI Lab starts on the $19 tier with one sport and five stored prompts, which is enough for a full v1-versus-v2 comparison in football. Open a kostenlos trial to run it on today's card, or read the prompt library Überblick for the shared structure behind every sport.
Football prompt questions
Why should a football prompt de-vig the Quoten first?
Because Buchmacher prices include a margin, so implied probabilities sum to more than 100%. If the model treats them as fair it will systematically overestimate every Ergebnis and see "value" where there is none. Removing the overround gives a baseline that is honest enough to argue with.
Where do I get xG numbers to paste in?
Any public source you already trust works, as long as you use the same source consistently — mixing providers introduces differences bigger than the effects you are trying to measure. On PropickAI Spiel pages the model and Markt Kontext are angezeigt alongside the Quoten, which is usually enough for the disciplined v1 prompt.
Do these prompts work for lower leagues?
The v1 Markt-anchored prompt travels well, because the price carries most of the information. The xG-driven v2 needs data that often does not exist below the top divisions — in that case either supply what you have or stick to v1.
How should the prompt treat the Unentschieden?
As a real Ergebnis with a real Wahrscheinlichkeit, not as a rounding error. Force three numbers that sum to 100% and compare the Unentschieden against the de-vigged Markt price. In tight, low-scoring leagues the Unentschieden is frequently the fairest price on the coupon, and a model that never Tipps it is telling you about its bias rather than about the Spiel.
Should I run one prompt bei every league, or write one per competition?
Starten with one prompt and one league so the comparison is clean, then widen. League Kontext (typical Tore, home advantage, refereeing) shifts the reference Punkte enough that a prompt tuned on the Premier League will misprice a low-scoring second division — which is exactly the kind of drift the AI Lab dashboard makes visible.
Prompts for the rest of the board
Find out which football prompt actually Siege
Starten the 5-day AI Lab trial without a card. Bring your own AI key, run v1 and v2 on today's football card, and let the dashboard settle it on a virtual $10,000 bank.
AI Lab $19/mo after the trial · cancel anytime · Vollzugang $49/mo for all sports and the official 7-AI consensus