Summary
Decentralized Finance (DeFi) transactions are complicated because many accounts, contracts, and tokens interact. The authors showed that looking at how these parts connect in small network patterns, called graphlets, helps identify different kinds of transaction methods. They combined counts of events with these network features and got better at telling transaction types apart. They also used a tool called SHAP to explain which network patterns were linked to which transaction methods.
What this means in practice
- •For blockchain developers: Improve tools for analyzing and categorizing DeFi transactions by incorporating network pattern analysis into transaction monitoring.
- •For financial compliance teams: Enhance automated detection and classification of DeFi activities to better monitor transaction types and detect unusual behaviors.
Authors
Célestin Coquidé, Alessio Brini, Natkamon Tovanich
Abstract
Decentralized Finance (DeFi) transactions involve complex interactions among accounts, smart contracts, and tokens. We investigate whether network topology can identify transaction methods that describe DeFi operations. We extract directed graphlet features to classify the 30 most frequent methods. Our results show that graphlet features complement event log counts in improving classification performance. Using SHapley Additive exPlanations (SHAP), we further derive model explanations that reveal method-specific graphlet structural patterns.