Identifying Likely-Reputable Blockchain Projects on Ethereum

2025-03-14

AI Summary

To address the challenge of distinguishing legitimate projects from fraudulent ones in the Ethereum ecosystem, this paper proposes a credibility assessment method based on multi-dimensional on-chain temporal behavioral modeling. We systematically integrate dynamic on-chain features—including inter-transaction time intervals (time_diff) and cumulative received transactions (received_tnx)—to construct a LightGBM classifier, augmented by on-chain transaction graph analysis and temporal feature engineering. Evaluated via 10-fold cross-validation on a balanced dataset comprising 2,179 fraudulent and 3,977 legitimate projects, the model achieves 98.4% accuracy and an AUC of 0.999. Key contributions include: (i) identifying time_diff and received_tnx as the most discriminative temporal indicators for credibility assessment; (ii) significantly enhancing model robustness and generalizability; and (iii) providing an interpretable, reusable machine learning framework for on-chain entity reputation evaluation.

Technology Category

• Machine Learning: Evaluation and Analysis
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization

Abstract

Identifying reputable Ethereum projects remains a critical challenge within the expanding blockchain ecosystem. The ability to distinguish between legitimate initiatives and potentially fraudulent schemes is non-trivial. This work presents a systematic approach that integrates multiple data sources with advanced analytics to evaluate credibility, transparency, and overall trustworthiness. The methodology applies machine learning techniques to analyse transaction histories on the Ethereum blockchain. The study classifies accounts based on a dataset comprising 2,179 entities linked to illicit activities and 3,977 associated with reputable projects. Using the LightGBM algorithm, the approach achieves an average accuracy of 0.984 and an average AUC of 0.999, validated through 10-fold cross-validation. Key influential factors include time differences between transactions and received_tnx. The proposed methodology provides a robust mechanism for identifying reputable Ethereum projects, fostering a more secure and transparent investment environment. By equipping stakeholders with data-driven insights, this research enables more informed decision-making, risk mitigation, and the promotion of legitimate blockchain initiatives. Furthermore, it lays the foundation for future advancements in trust assessment methodologies, contributing to the continued development and maturity of the Ethereum ecosystem.

Problem

• Identifying reputable Ethereum projects using advanced analytics.
• Distinguishing legitimate initiatives from fraudulent schemes on Ethereum.
• Enhancing trust and transparency in blockchain investments.

Innovation

• Integrates multiple data sources with advanced analytics
• Applies machine learning to analyze Ethereum transaction histories
• Uses LightGBM algorithm for high accuracy and AUC