Everyone ranks by money made. Money made is mostly luck.
Every trade on Polymarket’s international platform is public. Each trader is a persistent wallet, every fill is recorded on-chain, and anyone can replay the full history, which is why a whole industry of whale-trackers and copy tools exists. They all rank traders the same way: by how much money a wallet has made.
In April 2026, an academic working paper analyzed every Polymarket trade from 2023 to 2025 and tested that approach directly. The authors re-ran each trader’s positions thousands of times with randomized directions to establish what pure chance would produce. Among the biggest winners by raw money made, only about 12% beat the chance benchmark. Roughly 60% of the “lucky winners” became losers when tested on a separate set of events. About 3% of traders account for most of the market’s price discovery.
Coverage: CoinDesk, “Only 3% of traders drive prediction markets’ accuracy,” April 2026.
In plain terms: the number every tracker ranks by is mostly noise, and research now quantifies how much. OVERROUND exists to filter the noise out.
A raw record can lie
We built the scoring engine by hunting down, on real data, the many mechanisms that let an unskilled (or un-followable) wallet post a brilliant-looking record, from simple lucky streaks to automated market-making. Each one is identified and removed before a wallet is ranked. How we do that is part of what makes the ranking ours; the result is a board where a high position means a strong, independently verifiable historical record.
What we actually measure
OVERROUND scores a wallet’s accuracy in excess of the market price, computed over genuinely independent events, weighted by how much evidence the record actually contains, and ranked within each category.
The price baseline is the heart of it. A prediction market’s price is itself a forecast, so skill here has a precise meaning: beating the price. But the price carries known structural biases, and being on the right side of one of those is something anyone can do without information. We benchmark every fill against what the price alone would have paid, and credit only what remains.
One event per question.Markets that express one underlying question are collapsed into a single event before anything is scored, so repetition can’t masquerade as a track record. The wallets that rode the French election to the top of our early boards collapsed from many markets to one event each and disappeared.
Correcting the price baseline.We remove the structural premium in the price, so harvesting an overpriced longshot nets roughly zero, while leaving genuine, information-driven accuracy fully credited. Measuring the market’s own structure to do this surfaced microstructure findings we’re preparing to publish separately; one of them is the reason we deliberately refuseto “correct” a particular regime where the apparent advantage is actually the footprint of informed flow. Demeaning it would erase exactly the skill the leaderboard exists to find.
Evidence-weighted records.Raw averages over small samples are noise. Each wallet’s record is pulled toward its category baseline in proportion to how little independent evidence backs it: four lucky wins shrink to nearly nothing; a hundred consistent events barely move.
Ranks within category. With several hundred thousand candidate wallets, any fixed cutoff admits thousands by chance. We rank within category and take the top of each, and our top wallets stay on top under every reasonable variant of the scoring we tested.
From leaderboard to alerts.Statistical skill is necessary but not sufficient. Before a wallet generates alerts it passes structural and behavioral screens that remove the market-makers and the un-followable, and we exclude markets that resolve too fast to act on. Each position then clears a conviction gate: at least $1,000 of notional, sized meaningfully above that wallet’s own typical position, at a price a copier can still act on. Every alert meets conviction criteria built from wallet history, position size relative to that wallet’s norm, timing, and market followability, and every alert states why it qualified and, when the data shows one, a reason to be careful.
Building the referee forced us to measure how the market itself behaves. Two of those measurements stand on their own as empirical findings about prediction-market microstructure, and we intend to publish them in their own right.
What subscribers receive
On replayed recent history the watchlist surfaces roughly ten sizeable positions a day over the notional floor. The conviction gate passes roughly a third of those: in live operation, a handful of conviction alerts a day, three to five in a typical stretch, each one sized with conviction for that wallet at a price you can still act on. The largest single positions reach six figures. Delivery is a push for every alert, typically minutes after the move lands on-chain, plus a scheduled daily digest sent even on quiet days, with per-subscriber filters for size, category, and specific wallets. Fewer, better alerts is the deliberate trade: the filtered-out stream still exists, and we publish how both perform.
The data
Trade history is founded on the public Polymarket-v1 archive (Qin and Yang, Time Seventeen; CC-BY-4.0): every fill from the first trade in November 2022 through the contract migration in April 2026, with ground-truth trade direction. The current generation of the exchange is appended from the chain on an ongoing basis. We keep hundreds of millions of resolved fills under two documented policies: high-frequency series families are not stored (they are the majority of raw volume and collapse to a single event anyway), and rows that fail basic integrity checks are dropped and counted.
Honest limitations
The price baseline is estimated over the same history it is applied to, which introduces mild in-sample bias we accept for a leaderboard. Scores describe the past; no method makes past accuracy predict the future. The venue charges a dynamic fee at contested prices; current scores are computed before fees, and a fee adjustment is planned. OVERROUND scores the international Polymarket platform only, because it is the only venue whose per-trader records are public.
Methodology versions
The methodology is the product, so changes to scoring or alert selection are announced here rather than slipped in quietly.
v1.0 · July 2026.Initial public methodology: price-relative scoring over independent events, sample-size-aware shrinkage, within-category ranks, market-maker and followability screens, and the conviction gate on alerts (live July 4, 2026, replacing a flat notional floor). Cadence figures on this page describe the gated feed.
Planned. Fee-adjusted scoring for the fee era the venue introduced in February 2026. Current scores are computed before fees, as noted above.
OVERROUND is an information and analytics subscription built on publicly available data. It is not financial or investment advice, and it does not recommend that you enter any trade or contract; past accuracy does not predict future outcomes. We do not accept stakes, hold customer funds, or custody cryptocurrency.