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 | 24 | 4% | 38% | 33.1% |
| 0.10-0.20 | 10 | 16% | 40% | 24.0% |
| 0.20-0.30 | 7 | 25% | 14% | 10.7% |
| 0.30-0.40 | 17 | 35% | 29% | 6.1% |
| 0.40-0.50 | 46 | 46% | 11% | 34.8% |
| 0.50-0.60 | 24 | 54% | 25% | 29.5% |
| 0.60-0.70 | 9 | 65% | 56% | 9.1% |
| 0.70-0.80 | 6 | 75% | 33% | 41.7% |
| 0.80-0.90 | 2 | 85% | 100% | 15.2% |
Skill measures calibration quality (0-100). Variance measures return volatility (0-100, higher = more volatile).
On-chain verification: wallet age 450 days, 2000 txs, provenance grade B. Bot score: 0/100, wash trading score: 0/100.
Polymarket on-chain coverage: $4,422 in / $0 out across 3 withdrawal tx since 2025-02-14.
3100 total trades across 147 markets.
145 bets on resolved markets available for calibration scoring.
Calibration error: 26.8% — needs improvement.
Skill: 32/100 (calibration quality). Variance: 98/100 (higher = more volatile returns).
Brier Skill Score: -27.9% vs naive baseline (>0% = better than always predicting base rate).
Brier decomposition: REL=0.0839 RES=0.0247 UNC=0.1966.
Log loss: 0.7484 (skill: -28.5% vs naive). Lower log loss = better calibration on rare events.
Timeliness: avg entry 3.9 days before resolution, 0% early mover.
This trader shows some skill signal, but not enough to clearly distinguish from luck. More data needed.
Confidence: C/60 [CI95: C→C, 58-62] (145 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.