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 |
|---|---|---|---|---|
| 0.10-0.20 | 6 | 15% | 0% | 14.8% |
| 0.20-0.30 | 5 | 26% | 0% | 26.0% |
| 0.30-0.40 | 4 | 35% | 0% | 35.0% |
| 0.40-0.50 | 4 | 47% | 0% | 47.3% |
| 0.50-0.60 | 7 | 54% | 0% | 54.4% |
| 0.60-0.70 | 3 | 64% | 0% | 64.3% |
| 0.70-0.80 | 1 | 72% | 0% | 72.0% |
| 0.80-0.90 | 1 | 82% | 0% | 82.0% |
Skill measures calibration quality (0-100). Variance measures return volatility (0-100, higher = more volatile).
On-chain verification: wallet age 8 days, 2580 txs, provenance grade C. Bot score: 10/100, wash trading score: 50/100.
888 total trades across 585 markets.
31 bets on resolved markets available for calibration scoring.
Calibration error: 41.2% — needs improvement.
Skill: 11/100 (calibration quality). Variance: 9/100 (higher = more volatile returns).
Brier Skill Score: 17.7% vs naive baseline (>0% = better than always predicting base rate).
Brier decomposition: REL=0.2052 RES=0.0000 UNC=0.0000.
Log loss: 0.5926 (skill: -7394.1% vs naive). Lower log loss = better calibration on rare events.
Timeliness: avg entry 1.7 days before resolution, 0% early mover.
Below average. The data shows poor calibration, thin evidence, or both. When this trader expresses high confidence, events don't happen at the rate they imply.
Confidence: D/48 ± 15 (low confidence, 31 resolved bets). Low confidence — take this score with a grain of salt until more markets resolve.
Methodology: Brier Score Decomposition (Murphy 1973), Log Loss, On-Chain USDC Verification. Same approach used by IARPA to identify superforecasters.