Description
TL;DR: A network-analysis companion to the authors' machine-learning study, emphasizing graph-growth laws and local outlier factor on Bitcoin user and transaction graphs.
About This Document
Thai T. Pham and Steven Lee model Bitcoin activity as two networks, one centered on users and one on transactions. They examine degree distributions and densification, then apply k-means followed by local outlier factor to identify nodes whose neighborhoods look unusual. The approach is deliberately unsupervised because the public ledger does not label a user or transaction as legitimate or illicit.
Why Bitcoin People May Care
This document is distinct from the authors' shorter paper using Mahalanobis distance and support-vector methods. Here the emphasis is local graph structure and network evolution. The same caution remains: an outlier score is not proof of fraud, identity, or intent. The analysis reflects a 2016 dataset and research workflow, not current chain-surveillance capability or a compliance determination.
What You Receive
Purchase reveals the verified preserved PDF location for this document.
Document Details
- Title: Anomaly Detection in the Bitcoin System: A Network Perspective
- Author / organization: Thai T. Pham and Steven Lee
- Year: 2016
- Language: English
- Document type: Network-analysis research paper
- Pages: 8
CacheRat provides researched source-location and document-identification information. CacheRat does not claim ownership of the underlying third-party documentation.
