Week 16 Trading Results
Our ML models traded 202 positions across 7 sports this week, with a 58.4% win rate and +$13.89 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 |
|---|---|---|---|---|---|
| NHL | 40 | 28W-12L | 70.0% | 8.5c | +$22.11 |
| MLB | 72 | 51W-21L | 70.8% | 8.9c | +$15.39 |
| ATP | 18 | 9W-9L | 50.0% | -1.5c | -$0.03 |
| SOCCER | 8 | 3W-5L | 37.5% | -1.8c | -$0.18 |
| LOL | 23 | 10W-13L | 43.5% | -1.9c | -$0.22 |
| NBA | 12 | 6W-6L | 50.0% | -15.7c | -$10.34 |
| CS2 | 29 | 11W-18L | 37.9% | -18.8c | -$12.84 |
Notable Wins
- Moro Canas A. (ATP): Bought at 29c, fair value 50c, edge +20c
- G2 Esports (LOL): Bought at 31c, fair value 74c, edge +44c
- KIWOOM DRX (LOL): Bought at 33c, fair value 56c, edge +26c
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.