Reproduce “Clustering and analysis of user behaviour in blockchain: A case study of Planet IX” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Dorottya Zelenyanszki, Zhe Hou, Kamanashis Biswas, Vallipuram Muthukkumarasamy
Researchers at Griffith University and Australian Catholic University analyzed user behavior in the blockchain game Planet IX by processing on-chain transaction data. They applied graph-based analysis and machine learning techniques to categorize users into six distinct behavioral clusters, thereby demonstrating how public blockchain data can reveal detailed interaction patterns and highlighting associated privacy implications.
Key insights
- On-chain transaction data from blockchain applications can be processed with graph-based analysis and machine learning to reveal detailed, identifiable user behavior patterns.
- User behavior in blockchain games can be categorized into distinct clusters, such as 'Dropouts,' 'Active Users,' and 'Inactive Users with Interest,' based on their engagement, NFT usage, and activity preferences.
- The transparency of blockchain, coupled with sophisticated analysis techniques, poses significant privacy risks, including targeted marketing, secondary market exploitation, impersonation attacks, and de-anonymization.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.