aiqbench takeMachine Learning

This research applies graphlet-based network topology analysis to classify DeFi transaction methods, demonstrating that structural features significantly enhance classification accuracy over simple event logs. By integrating SHAP for model interpretability, the study reveals specific graphlet patterns inherent to different DeFi operations, offering a novel approach to analyzing blockchain activity through machine learning.

Source coveringarXiv

What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

Graphlet-based Decentralized Finance Transaction Method Classification

arXivOctober 19, 20261 min read

arXiv:2610.23466v1 Announce Type: cross 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.

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.

Social and Information Networks (cs.SI); Computational Engineering, Finance, and Science (cs.CE); Computers and Society (cs.CY); Emerging Technologies (cs.ET); Machine Learning (cs.LG)

arXiv:2610.23466 [cs.SI]

(or arXiv:2610.23466v1 [cs.SI] for this version)

https://doi.org/10.48550/arXiv.2610.23466 arXiv-issued DOI via DataCite (pending registration)

Full text under the publisher's open licence · 104 words

Read at arXiv ↗Ask about this article