Clustering Ethereum Addresses

Clustering Ethereum AddressesCategorizing addresses using patterns in transaction activityWill PriceBlockedUnblockFollowFollowingDec 6IntroductionEthereum users may be anonymous, but their addresses are unique identifiers that leave a trail publicly visible on the blockchain.I built a clustering algorithm based on transaction activity that divides Ethereum users into distinct behavioral subgroups..Because Ethereum addresses are unique identifiers whose ownership does not change, their activity can be tracked, aggregated, and analyzed.Here, I attempt to create user archetypes by effectively clustering the Ethereum address space..To separate them, I performed a second round of clustering, using only the addresses in that cluster.By changing the dissimilarity measure from euclidean distance to cosine distance, I dramatically improved separation between exchanges and miners.By substituting results from re-clustering into the original analysis, we end up with 9 clusters.Interpreting the ResultsWe can draw conclusions about user behavior based on the corresponding cluster centroids.Radar plot — cluster centroid address featuresExchangesHigh ether balanceHigh incoming and outgoing transaction volumeHighly irregular time between transactionsExchanges are the banks of the crypto space.. More details

Leave a Reply