Week 15 Trading Results
Our ML models traded 147 positions across 9 sports this week, with a 57.8% win rate and +$69.01 net P&L.
Every trade is executed on Polymarket and verified on PolygonScan.
Performance by Sport
| Sport | Trades | Record | Win Rate | c/Trade | P&L |
|---|---|---|---|---|---|
| NBA | 6 | 2W-4L | 33.3% | -17.0c | +$31.04 |
| ATP | 12 | 8W-4L | 66.7% | 22.6c | +$15.13 |
| NCAAWB | 3 | 3W-0L | 100.0% | 45.3c | +$10.01 |
| LOL | 16 | 10W-6L | 62.5% | 16.3c | +$6.92 |
| NCAAMB | 4 | 4W-0L | 100.0% | 27.2c | +$4.85 |
| CS2 | 44 | 19W-25L | 43.2% | 4.2c | +$1.65 |
| SOCCER | 3 | 2W-1L | 66.7% | 7.0c | +$1.11 |
| MLB | 33 | 21W-12L | 63.6% | -0.5c | +$0.18 |
| NHL | 26 | 16W-10L | 61.5% | 0.9c | -$1.88 |
Notable Wins
- Zarazua R. (ATP): Bought at 28c, fair value 63c, edge +35c
- Zarazua R. (ATP): Bought at 31c, fair value 63c, edge +35c
- BNK FEARX (LOL): Bought at 32c, fair value 85c, edge +55c
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.