Week 18 Trading Results
Our ML models traded 161 positions across 8 sports this week, with a 39.8% win rate and -$61.94 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 | 31 | 14W-17L | 45.2% | 1.0c | +$0.20 |
| SOCCER | 9 | 3W-6L | 33.3% | -6.9c | -$0.82 |
| NBA | 11 | 7W-4L | 63.6% | -5.3c | -$2.81 |
| NHL | 6 | 3W-3L | 50.0% | -21.0c | -$7.31 |
| WTA | 16 | 6W-10L | 37.5% | -7.2c | -$8.55 |
| MLB | 17 | 4W-13L | 23.5% | -29.1c | -$12.65 |
| LOL | 24 | 11W-13L | 45.8% | -4.7c | -$12.99 |
| CS2 | 47 | 16W-31L | 34.0% | -13.9c | -$17.01 |
Notable Wins
- away (SOCCER): Bought at 34c, fair value 46c, edge +12c
- Pliskova K. (ATP): Bought at 35c, fair value 61c, edge +29c
- Pliskova K. (ATP): Bought at 35c, fair value 61c, edge +29c
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.