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 | 8 | 8% | 25% | 17.3% |
| 0.10-0.20 | 4 | 13% | 50% | 37.1% |
| 0.30-0.40 | 2 | 33% | 100% | 67.2% |
| 0.40-0.50 | 4 | 41% | 50% | 9.4% |
| 0.50-0.60 | 34 | 50% | 71% | 20.6% |
Skill measures calibration quality (0-100). Variance measures return volatility (0-100, higher = more volatile).
On-chain verification: wallet age 404 days, 2579 txs, provenance grade A. Bot score: 40/100, wash trading score: 50/100.
2000 total trades across 19 markets.
52 bets on resolved markets available for calibration scoring.
Calibration error: 22.3% — needs improvement.
Skill: 39/100 (calibration quality). Variance: 47/100 (higher = more volatile returns).
Brier Skill Score: -10.9% vs naive baseline (>0% = better than always predicting base rate).
Brier decomposition: REL=0.0610 RES=0.0336 UNC=0.2367.
Log loss: 0.7358 (skill: -10.4% 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/59 ± 8 (medium confidence, 52 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.