Independent wallets, not big wallets
One actor running six addresses is one opinion. Getting that distinction right matters more than expanding coverage.
The hardest problem in this space is not finding wallets. It is knowing which wallets are the same person.
Why one desk isn't a pattern
Every alert we publish rests on a claim: that several separate participants decided the same thing at roughly the same time. If that claim is wrong, if the six wallets are one desk splitting an order, then the alert is not a pattern. It is one trade, dressed up as consensus, and it is worse than no alert at all because it feels like confirmation.
Why independence is scored separately from wallet count
This is why we weight independence as its own input rather than folding it into the wallet count. A cluster of six addresses that resolve to two actors scores materially lower than a cluster of four addresses that resolve to four. Both appear on the surface as "multiple wallets buying." Only one of them is information. This is one of the seven weighted components behind every score, laid out in full on methodology.
Why we stopped starting from known entities
The instinct when building a wallet dataset is to start from known entities, exchanges, market makers, public funds, and grow outward from labels. We tried that and it stalled: the labels were accurate and the coverage was useless. What worked was inverting it. Group wallets by how they behave first, and treat identity as a secondary, optional question. You do not need to know who an actor is to know that two addresses are probably the same actor, and for our purposes the second fact is the one that changes the score.
What we won't publish, and why
We are not going to publish the specific signals we use to make that judgement. They are the part of the system a competitor would most like to have, and they are also the part most easily gamed by anyone who wants their flow to look like a crowd. What we will say is that the test is behavioural and continuous, not a one-off label, and that it is applied on all four chains by automated crawlers rather than by a labelling team, see chain coverage for where that runs today.
The coverage tradeoff we accept
The corollary is a bias we will defend. We would rather track fewer wallets we understand than a large number we do not. A bigger tracked set is an easy number to advertise and a poor proxy for signal quality, the marginal wallet in a bloated set is usually a bot, a bridge, or a duplicate, and each of those actively degrades the feed. Coverage grows every day, but it grows on the crawler's terms, not on a marketing target's. See how this plays out in practice on the track record page, which publishes both hits and misses.
Frequently asked questions
Why not just track more wallets?
Because a bigger tracked set is a worse proxy for quality, not a better one. The marginal wallet added to a bloated dataset is usually a bot, a bridge, or a duplicate address, and each of those degrades the feed rather than improving coverage. We'd rather track fewer wallets we understand than a large number we don't.
Doesn't behavioral clustering risk false positives, treating independent actors as one?
It's a real tradeoff, which is why the test is continuous rather than a one-off label. Wallets aren't permanently tagged as "same actor," their relationship is re-evaluated as behavior accumulates, and independence is scored as its own input rather than assumed from wallet count alone.
Why won't SpotX publish the specific signals used to detect coordinated wallets?
Because publishing them would hand the exact playbook to anyone trying to make coordinated flow look like independent consensus, which is the one thing this system exists to catch. The commitment we do make public is the behavioral, continuous nature of the test and the fact that it runs on all four chains through automated crawlers, not a labelling team.
Is wallet clustering applied the same way across all four chains?
The same behavioral, continuous approach runs across all four supported chains, Solana, Hyperliquid, Base, and Ethereum, through automated crawlers rather than manual labelling. Chain-specific consolidation and cooldown windows differ, which is detailed on the methodologyLink page.