Analyzing Blockchain Data to Detect Bitcoin Addresses Involved in Illicit Activities Using Anomaly Detection

The popularity of cryptocurrency has continued to spike in recent years, and among them, bitcoin still remains the most popular. Perhaps the biggest reason for its popularity is the blockchain technology that it is built on. While the technology prevents fraud on the network, there are no checks to track how the bitcoins are being used and for what purpose. Our study tries to investigate the block data stored on the bitcoin blockchain to gain insight and build relationships between transactions that can shed light on the transactions and identify the bitcoin addresses involved in illicit activities. This is carried out by using the HPCC systems analytics platform for ingesting the data. Anomaly detection technique has been used by using a set of specialized features based on transaction behavior where anomalies in users are examined as opposed to anomalies in individual addresses. The K-means algorithm has been used for clustering of data. This study successfully yielded addresses which were potentially involved in illicit activities including involvement in the Mt. Gox hack of 2014.