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 | 554 | 4% | 13% | 8.6% |
| 0.10-0.20 | 62 | 14% | 10% | 4.6% |
| 0.20-0.30 | 12 | 23% | 0% | 23.1% |
| 0.30-0.40 | 8 | 34% | 0% | 34.2% |
| 0.40-0.50 | 2 | 43% | 0% | 43.5% |
| 0.50-0.60 | 2 | 54% | 0% | 54.0% |
| 0.60-0.70 | 6 | 66% | 0% | 66.2% |
| 0.70-0.80 | 2 | 79% | 0% | 78.8% |
| 0.80-0.90 | 28 | 87% | 7% | 79.6% |
| 0.90-1.00 | 42 | 94% | 0% | 94.0% |
Skill measures calibration quality (0-100). Variance measures return volatility (0-100, higher = more volatile).
On-chain verification: wallet age 12 days, 2982 txs, provenance grade C. Bot score: 50/100, wash trading score: 50/100.
2000 total trades across 317 markets.
718 bets on resolved markets available for calibration scoring.
Calibration error: 17.4% — good.
Skill: 39/100 (calibration quality). Variance: 33/100 (higher = more volatile returns).
Brier Skill Score: -91.8% vs naive baseline (>0% = better than always predicting base rate).
Brier decomposition: REL=0.0912 RES=0.0016 UNC=0.0990.
Log loss: 0.6680 (skill: -91.1% 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/51 ± 3 (high confidence, 718 resolved bets). This score is highly reliable — enough resolved bets to be confident.
Methodology: Brier Score Decomposition (Murphy 1973), Log Loss, On-Chain USDC Verification. Same approach used by IARPA to identify superforecasters.