Week 17 Trading Results
Our ML models traded 138 positions across 8 sports this week, with a 49.3% win rate and +$2.74 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 |
|---|---|---|---|---|---|
| ATP | 25 | 12W-13L | 48.0% | 0.7c | +$8.05 |
| CS2 | 18 | 11W-7L | 61.1% | 13.7c | +$7.37 |
| NHL | 15 | 8W-7L | 53.3% | -1.2c | +$2.96 |
| NBA | 7 | 4W-3L | 57.1% | -9.9c | +$1.11 |
| LOL | 14 | 5W-9L | 35.7% | -9.1c | -$0.48 |
| MLB | 25 | 15W-10L | 60.0% | 1.7c | -$2.42 |
| SOCCER | 13 | 3W-10L | 23.1% | -22.2c | -$4.25 |
| WTA | 21 | 10W-11L | 47.6% | -5.4c | -$9.60 |
Notable Wins
- Relove Deep Cross Gaming (LOL): Bought at 32c, fair value 62c, edge +27c
- Vitality (CS2): Bought at 35c, fair value 68c, edge +26c
- Lorenzo Sonego (ATP): Bought at 36c, fair value 51c, edge +17c
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.