The first player-level strategy: a gradient-boosted scorer model (rolling goals/shots per 90, starting rate, team attack vs opponent defence, confirmed lineups when available) prices every Kalshi anytime-goalscorer market and bets where its probability beats the fee-adjusted ask by 10%+. Settles from Kalshi's own results.
football · Anytime goalscorer (1+) · status: live · betting forward from 2026-07-04 · same $1000 start as every other strategy
| Bet | Stake | Odds | To win | Model edge | P&L | Status |
|---|---|---|---|---|---|---|
Kylian Mbappe in France v Spain · Anytime goalscorer (1+) @ 2.09 | $5.00 | 2.09 | $5.47 | +10% | — | pending |
Lionel Messi in England v Argentina · Anytime goalscorer (1+) @ 2.34 | $5.00 | 2.34 | $6.71 | +17% | — | pending |
Manuel Akanji in Argentina v Switzerland · Anytime goalscorer (1+) @ 31.21 | $5.00 | 31.21 | $151.07 | +17% | -5.00 | lost |
Granit Xhaka in Argentina v Switzerland · Anytime goalscorer (1+) @ 18.75 | $5.00 | 18.75 | $88.76 | +25% | -5.00 | lost |
Fabian Ruiz in Spain v Belgium · Anytime goalscorer (1+) @ 6.74 | $5.00 | 6.74 | $28.69 | +11% | +28.69 | won |
Alexis Saelemaekers in Spain v Belgium · Anytime goalscorer (1+) @ 8.50 | $5.00 | 8.50 | $37.50 | +16% | -5.00 | lost |
Mohamed Salah in Argentina v Egypt · Anytime goalscorer (1+) @ 5.25 | $5.00 | 5.25 | $21.27 | +11% | -5.00 | lost |
Ruben Vargas in Switzerland v Colombia · Anytime goalscorer (1+) @ 8.56 | $5.00 | 8.56 | $37.79 | +62% | -5.00 | lost |
Breel Embolo in Switzerland v Colombia · Anytime goalscorer (1+) @ 3.80 | $5.00 | 3.80 | $14.00 | +38% | -5.00 | lost |
Julian Quinones in Mexico v England · Anytime goalscorer (1+) @ 3.08 | $5.00 | 3.08 | $10.39 | +16% | +10.39 | won |
Stephen Eustaquio in Canada v Morocco · Anytime goalscorer (1+) @ 23.43 | $5.00 | 23.43 | $112.13 | +22% | -5.00 | lost |
Jonathan David in Canada v Morocco · Anytime goalscorer (1+) @ 4.73 | $5.00 | 4.73 | $18.67 | +52% | -5.00 | lost |
Julio Enciso in Paraguay v France · Anytime goalscorer (1+) @ 9.41 | $5.00 | 9.41 | $42.04 | +49% | -5.00 | lost |
"Model edge" = model probability × odds − 1 at the moment of betting: the profit the model expected per $1. Positive edge can still lose (single bets usually do) — the question is whether edges are positive on average AND the model's probabilities are honest.