Week 19 Trading Results
Our ML models traded 70 positions across 7 sports this week, with a 27.1% win rate and -$69.42 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 |
|---|---|---|---|---|---|
| NBA | 1 | 0W-1L | 0.0% | -44.0c | -$1.41 |
| CS2 | 7 | 3W-4L | 42.9% | -0.4c | -$2.42 |
| NHL | 3 | 0W-3L | 0.0% | -29.3c | -$5.02 |
| MLB | 29 | 12W-17L | 41.4% | -3.6c | -$5.53 |
| WTA | 8 | 3W-5L | 37.5% | -17.6c | -$7.83 |
| LOL | 6 | 1W-5L | 16.7% | -32.7c | -$14.72 |
| ATP | 16 | 0W-16L | 0.0% | -52.8c | -$32.49 |
Notable Wins
- kansascityroyals (MLB): Bought at 28c, fair value 42c, edge +14c
- kansascityroyals (MLB): Bought at 35c, fair value 35c, edge +0c
- tampabayrays (MLB): Bought at 36c, fair value 38c, edge +2c
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.