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 | 3 | 29% | 0% | 29.2% |
| 0.30-0.40 | 143 | 36% | 0% | 36.1% |
| 0.40-0.50 | 42 | 43% | 0% | 42.7% |
| 0.50-0.60 | 1 | 57% | 0% | 57.0% |
| 0.60-0.70 | 1 | 70% | 0% | 69.6% |
Skill measures calibration quality (0-100). Variance measures return volatility (0-100, higher = more volatile).
On-chain verification: wallet age 72 days, 2000 txs, provenance grade C. Bot score: 0/100, wash trading score: 0/100.
Polymarket on-chain coverage: $1,642 in / $0 out across 115 withdrawal tx since 2026-02-10.
3100 total trades across 191 markets.
190 bets on resolved markets available for calibration scoring.
Calibration error: 37.8% — needs improvement.
Skill: 15/100 (calibration quality). Variance: 14/100 (higher = more volatile returns).
Brier Skill Score: 42.1% vs naive baseline (>0% = better than always predicting base rate).
Brier decomposition: REL=0.1441 RES=0.0000 UNC=0.0000.
Log loss: 0.4773 (skill: -5935.7% vs naive). Lower log loss = better calibration on rare events.
Timeliness: avg entry 0.6 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 ± 8 (medium confidence, 190 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.