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 |
|---|---|---|---|---|
| 0.20-0.30 | 5 | 24% | 0% | 23.8% |
| 0.30-0.40 | 6 | 36% | 0% | 36.1% |
| 0.40-0.50 | 4 | 47% | 0% | 46.5% |
| 0.50-0.60 | 6 | 55% | 0% | 54.9% |
| 0.60-0.70 | 2 | 64% | 0% | 64.2% |
| 0.70-0.80 | 2 | 74% | 50% | 23.5% |
| 0.80-0.90 | 1 | 85% | 100% | 15.0% |
Skill measures calibration quality (0-100). Variance measures return volatility (0-100, higher = more volatile).
On-chain verification: wallet age 898 days, 2356 txs, provenance grade A. Bot score: 30/100, wash trading score: 50/100.
1619 total trades across 294 markets.
26 bets on resolved markets available for calibration scoring.
Calibration error: 40.1% — needs improvement.
Skill: 20/100 (calibration quality). Variance: 25/100 (higher = more volatile returns).
Brier Skill Score: -184.2% vs naive baseline (>0% = better than always predicting base rate).
Brier decomposition: REL=0.1808 RES=0.0518 UNC=0.0710.
Log loss: 0.5883 (skill: -116.9% vs naive). Lower log loss = better calibration on rare events.
Timeliness: avg entry 7.4 days before resolution, 8% 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/37 ± 15 (low confidence, 26 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.