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 | 28 | 3% | 14% | 10.8% |
| 0.10-0.20 | 24 | 16% | 0% | 15.7% |
| 0.20-0.30 | 46 | 26% | 0% | 25.7% |
| 0.30-0.40 | 124 | 35% | 0% | 35.0% |
| 0.40-0.50 | 210 | 45% | 0% | 44.9% |
| 0.50-0.60 | 262 | 54% | 0% | 54.5% |
| 0.60-0.70 | 160 | 64% | 0% | 64.1% |
| 0.70-0.80 | 66 | 74% | 0% | 74.3% |
| 0.80-0.90 | 30 | 85% | 0% | 84.7% |
| 0.90-1.00 | 44 | 96% | 5% | 91.3% |
Skill measures calibration quality (0-100). Variance measures return volatility (0-100, higher = more volatile).
On-chain verification: wallet age 26 days, 3000 txs, provenance grade C. Bot score: 30/100, wash trading score: 80/100.
2000 total trades across 1923 markets.
994 bets on resolved markets available for calibration scoring.
Calibration error: 51.9% — needs improvement.
Skill: 0/100 (calibration quality). Variance: 9/100 (higher = more volatile returns).
Brier Skill Score: -5022.2% vs naive baseline (>0% = better than always predicting base rate).
Brier decomposition: REL=0.3012 RES=0.0006 UNC=0.0060.
Log loss: 0.8821 (skill: -2292.9% vs naive). Lower log loss = better calibration on rare events.
No demonstrated forecasting skill. This trader performs at or below random chance based on available data.
Confidence: F/34 ± 3 (high confidence, 994 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.