Decoding Decentralized Finance Transactions through Ego Network Motif Mining

TL;DR

It is demonstrated that smart contract methods performing specific DeFi operations can be efficiently identified by analyzing these motifs while providing insights into account activities, and a method to extract ego network motifs from the token transfer network is presented.

Abstract

Decentralized Finance (DeFi) is increasingly studied and adopted for its potential to provide accessible and transparent financial services. Analyzing how investors use DeFi is important for reaching a better understanding of their usage and for regulation purposes. However, analyzing DeFi transactions is challenging due to often incomplete or inaccurate labeled data. This paper presents a method to extract ego network motifs from the token transfer network, capturing the transfer of tokens between users and smart contracts. Our results demonstrate that smart contract methods performing specific DeFi operations can be efficiently identified by analyzing these motifs while providing insights into account activities.

Figures (8)

• Figure 1: (a) Fund accounts in our dataset and (b) Token transfers histogram
• Figure 2: List of all possible ego network motifs
• Figure 3: Examples of transaction description by motifs and edge lists
• Figure 4: Comparison of classification results with 10-fold CV scores
• Figure 5: Confusion metric from the decision tree model using $M+E$ features