Week 22 Trading Results
Our ML models traded 232 positions across 9 sports this week, with a 42.2% win rate and -$24.40 net P&L.
Every trade is executed on Polymarket and verified on-chain.
Performance by Sport
| Sport | Trades | Record | Win Rate | c/Trade | P&L |
|---|---|---|---|---|---|
| WNBA | 7 | 5W-2L | 71.4% | 33.7c | +$9.24 |
| NHL | 5 | 3W-2L | 60.0% | 10.8c | +$3.76 |
| SOCCER | 15 | 10W-5L | 66.7% | 19.1c | +$2.86 |
| LOL | 25 | 11W-14L | 44.0% | 3.8c | +$1.15 |
| CS2 | 13 | 5W-8L | 38.5% | -3.5c | -$1.78 |
| MLB | 47 | 23W-24L | 48.9% | -3.5c | -$2.11 |
| WTA | 63 | 30W-33L | 47.6% | -2.8c | -$6.00 |
| ATP | 57 | 11W-46L | 19.3% | -12.9c | -$31.52 |
Notable Wins
- tampabayrays (MLB): Bought at 24c, fair value 23c, edge +1c
- losangelessparks (WNBA): Bought at 25c, fair value 31c, edge +6c
- Alex de Minaur (ATP): Bought at 25c, fair value 50c, edge +25c
How It Works
Our models are trained on 60,000+ historical games and predict fair win probability from game state alone — score, time, period, Elo ratings. When our fair probability exceeds the market ask by 8c+, we buy and hold to settlement.