When this trader buys at $0.70, they imply 70% probability. Perfect calibration = the event happens 70% of the time.
| Bucket | Bets | Expected | Actual | Error |
|---|---|---|---|---|
| 0.00-0.10 | 6 | 3% | 0% | 3.4% |
| 0.20-0.30 | 6 | 22% | 100% | 78.0% |
| 0.30-0.40 | 14 | 37% | 71% | 34.9% |
| 0.40-0.50 | 12 | 44% | 50% | 5.9% |
| 0.50-0.60 | 14 | 54% | 43% | 11.6% |
| 0.60-0.70 | 4 | 64% | 50% | 14.3% |
| 0.70-0.80 | 4 | 71% | 50% | 21.2% |
| 0.80-0.90 | 2 | 80% | 100% | 19.8% |
Skill measures calibration quality (0-100). Variance measures return volatility (0-100, higher = more volatile).
On-chain verification: wallet age 46 days, 2836 txs, provenance grade B. Bot score: 40/100, wash trading score: 20/100.
2000 total trades across 436 markets.
62 bets on resolved markets available for calibration scoring.
Calibration error: 22.4% — needs improvement.
Skill: 44/100 (calibration quality). Variance: 81/100 (higher = more volatile returns).
Brier Skill Score: -11.0% vs naive baseline (>0% = better than always predicting base rate).
Brier decomposition: REL=0.0957 RES=0.0656 UNC=0.2477.
Log loss: 0.7389 (skill: -7.3% vs naive). Lower log loss = better calibration on rare events.
This trader shows some skill signal, but not enough to clearly distinguish from luck. More data needed.
Confidence: C/55 ± 8 (medium confidence, 62 resolved bets). Moderate confidence — score may shift as more markets resolve.
Methodology: Brier Score Decomposition (Murphy 1973), Log Loss, On-Chain USDC Verification. Same approach used by IARPA to identify superforecasters.