Week 20 Trading Results
Our ML models traded 334 positions across 8 sports this week, with a 49.7% win rate and -$49.08 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 |
|---|---|---|---|---|---|
| MLB | 29 | 18W-11L | 62.1% | 2.3c | +$2.18 |
| LOL | 14 | 8W-6L | 57.1% | 6.9c | +$2.13 |
| ATP | 56 | 30W-26L | 53.6% | 2.6c | +$0.80 |
| SOCCER | 15 | 6W-9L | 40.0% | -1.6c | -$0.90 |
| NHL | 10 | 5W-5L | 50.0% | -2.6c | -$2.84 |
| NBA | 8 | 1W-7L | 12.5% | -20.5c | -$5.93 |
| CS2 | 84 | 42W-42L | 50.0% | -9.1c | -$20.93 |
| WTA | 118 | 56W-62L | 47.5% | -5.9c | -$23.59 |
Notable Wins
- Mattia Bellucci (ATP): Bought at 24c, fair value 48c, edge +23c
- philadelphiaphillies (MLB): Bought at 24c, fair value 39c, edge +14c
- Lilmix (CS2): Bought at 25c, fair value 26c, edge +1c
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.