Home / Oracles
Research data temporarily unreachable — retrying
Live feed temporarily unreachable — retrying
The Oracles

The Oracles — the best Polymarket traders, statistically validated

We call them Oracles: the Polymarket traders whose entries statistically precede the market's price move. Each one survived full-universe scanning, multiple-testing correction and an untouched holdout — then re-testing on complete, unbiased data. Identities are sealed and hash-committed, so the roster can never be rewritten.

Why it works

Validation summary

Every validated Oracle was re-tested on complete, unbiased position sets several times larger than the originals. All of them survived. Every one is publicly verifiable.

Backtest across 64 independent trade clusters: measured edge per trade +1.09% to +2.57% at 95% confidence — decisively above zero. 92% of the validated edge comes from sports markets.

What "validated" means here H0: lead = 0.5  →  BH-FDR= 0.05, m = 1,003)  →  holdout

A binomial test against chance on every profiled wallet, corrected for 1,003 simultaneous comparisons, then confirmed on an untouched chronological holdout — adjusted p-values run as low as 4.9×10⁻¹³¹. Full methodology →

The scoreboard

The wider field, ranked by expected value

Beyond the validated roster: every wallet the engine scored, ranked by expected value per dollar net of execution costs. Sortable — click any column.

[X]ORACLE TERMINAL v1.0
You have activated retro mode. The janitor nods approvingly and keeps mopping.
Nothing about the data changed — it was already real.
Score: 10 points.