Graphlet Features Enhance DeFi Transaction Classification

Researchers have developed a new method for classifying decentralized finance (DeFi) transactions using graphlet features extracted from transaction networks. This approach complements traditional event log counts, leading to improved classification performance for the 30 most frequent DeFi transaction methods. The study also utilized SHapley Additive Explanations (SHAP) to identify method-specific graphlet structural patterns, providing insights into the underlying transaction behaviors. AI

IMPACT This research could lead to more robust fraud detection and analysis in decentralized finance by leveraging network topology.

RANK_REASON The cluster contains a research paper detailing a new method for classifying decentralized finance transactions. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• CatalyzeX Code Finder for Papers
• CORE Recommender
• DagsHub
• decentralized finance
• Gotit.pub
• Hugging Face
• Influence Flower
• ScienceCast
• Shapley Additive Explanations

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →