AI football betting prompts built around xG and the fair price
サッカー is the hardest sport to prompt well: three 結果, low scoring, and the most efficient マーケット in betting. A prompt that ignores the 引き分け 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 ブックメーカーマージン out of the 1X2 prices so the モデル starts from a fair baseline instead of an inflated one. Everything after that is an adjustment — form measured in xG rather than ポイント, 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 引き分け honest. Roughly a quarter of 試合 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 確率 set that sums to 100%, so an under-weighted 引き分け becomes visible immediately instead of hiding inside a confident "home 勝利".
The third job is scale. サッカー 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 試合 page, and to say so when that is not enough.
De-vig before you predict
Convert 1X2 オッズ to implied probabilities, remove the overround, and treat the result as the baseline. A prompt that starts from raw オッズ is starting from a number that already sums to more than 100%.
xG over results
Five-試合 samples of ゴール are almost noise. xG for and against, shot volume and shot quality tell you whether a run of 勝利数 is real. Value lives where the table lags the underlying performance.
ホーム-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 モデル 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 モデル cannot guess — you have to supply them.
サッカー prompts v1 and v2 — and how they differ
The same モデル, two instruction sets, two different betting personalities. Run both on the same 試合; that comparison is the only thing that settles the argument.
| Version | Focus | Style | Best for |
|---|---|---|---|
| v1 | 晴天 1X2 baseline, then small adjustments | Disciplined | 1X2, consistency |
| v2 | Shot quality and ゴール マーケット | ゴールs-hunting | Totals and BTTS value |
You are a disciplined football betting analyst. 試合: {home} vs {away}, {league}, {date}. マーケット 1X2: {オッズ}.
Step 1: convert the 1X2 オッズ to implied probabilities and remove the ブックメーカーマージン 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 引き分け honest: it is roughly 25% in most top leagues.
Output exactly:
1) ホーム / 引き分け / away probabilities summing to 100%
2) Main ピック + 信頼度 1-10
3) Best value マーケット (1X2 / オーバー-アンダー 2.5 / BTTS) and the reason
4) Most likely correct スコア
5) One-ライン reasoning
If your fair price 試合 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 ライン plays — not on results. Lean into ゴール マーケット when both attacks create real chances, and away from them when either side suppresses shot quality.
Compare every conclusion with the posted ライン {オッズ} and flag where the マーケット disagrees with the underlying numbers.
Output exactly:
1) Predicted スコア
2) オーバー/アンダー ピック with the ライン you are using
3) BTTS はい/no
4) 1X2 ピック + 信頼度 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 試合 in the AI Lab. Pasting into your own chat window works too — just replace them by hand.
What to feed the モデル, and what a usable answer looks like
Feed it this
- リーグ, matchweek and kick-off date — plus cup コンテキスト if the 試合 is a dead rubber.
- Last five 試合 per side with xG for and against, not just scorelines.
- ホーム 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 試合 and travel distance.
- The ライン: 1X2, オーバー-アンダー 2.5 and BTTS. 天気 too, if it is extreme.
Good output has
- Three probabilities for home / 引き分け / away summing to exactly 100%.
- A main ピック plus 信頼度 1-10, with a low スコア allowed.
- The best value マーケット of the three (1X2, オーバー-アンダー, BTTS) and why.
- A most-likely correct スコア, which exposes an incoherent 確率 set fast.
- One decisive factor in one ライン — no paragraph of hedging.
- A clear "no bet" when the fair price and the offered price 一致.
Where football prompts usually go wrong
- アンダー-weighting the 引き分け (it is around 25% in most top leagues).
- Reading one 4-0 as a step change instead of variance.
- Motivation narratives ("they need the 勝利") replacing data.
- Totals ピック that ignore how each side actually creates shots.
オッズ, モデル コンテキスト and マーケット drift for each fixture are on the football 試合 with オッズ and AI ピック board, so most of the input list above can be copied straight from the 試合 page.
Prompting the three マーケット football actually offers
A prompt that only answers "who 勝利数" throws away most of a football card. The three liquid マーケット 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 スコア that contradict each other tell you the モデル is guessing.
Three-way, 引き分け included
Demand three probabilities that sum to 100% and compare each with the de-vigged price. The 引き分け is the honesty test — a モデル that prices it under 20% in a tight league 試合 is not reasoning, it is picking a 本命.
Totals need shot creation, not results
オーバー-アンダー is a question about how each side generates and concedes chances: shot volume, shot quality, set-piece threat, defensive ライン height. Two チーム that both create little produce unders regardless of how attacking their reputations are.
両チーム得点 (BTTS)
BTTS is close to two independent scoring questions, so ask for each side's chance of scoring separately before the はい/no. It is also where a weak keeper or a missing centre-back moves the honest number most.
Handicaps and correct スコア
Ask for a most likely correct スコア even when you are not betting it: it exposes an incoherent 確率 set instantly. If the モデル says 55% home 勝利 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 試合
ピック 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 試合 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 無料 trial to run it on today's card, or read the prompt library 概要 for the shared structure behind every sport.
サッカー prompt questions
Why should a football prompt de-vig the オッズ first?
Because ブックメーカー prices include a margin, so implied probabilities sum to more than 100%. If the モデル treats them as fair it will systematically overestimate every 結果 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 出典 you already trust works, as long as you use the same 出典 consistently — mixing providers introduces differences bigger than the effects you are trying to measure. On PropickAI 試合 pages the モデル and マーケット コンテキスト are 表示 alongside the オッズ, which is usually enough for the disciplined v1 prompt.
Do these prompts work for lower leagues?
The v1 マーケット-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 引き分け?
As a real 結果 with a real 確率, not as a rounding error. Force three numbers that sum to 100% and compare the 引き分け against the de-vigged マーケット price. In tight, low-scoring leagues the 引き分け is frequently the fairest price on the coupon, and a モデル that never ピック it is telling you about its bias rather than about the 試合.
Should I run one prompt 横断 every league, or write one per competition?
開始 with one prompt and one league so the comparison is clean, then widen. リーグ コンテキスト (typical ゴール, home advantage, refereeing) shifts the reference ポイント enough that a prompt tuned on the Premier リーグ 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 勝利数
開始 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 · フルアクセス $49/mo for all sports and the official 7-AI consensus