Detecting Fraudulent Accounts on Blockchain: A Supervised Approach

TL;DR

This paper explores supervised machine learning methods to detect fraudulent accounts on the Ethereum blockchain, demonstrating effective classification performance and analyzing feature importance for anti-fraud applications.

Contribution

It introduces a comparative analysis of Random Forests, SVM, and XGBoost for blockchain fraud detection using a large dataset, highlighting their effectiveness and feature sensitivity.

Findings

Achieved high recall and precision in fraud detection

XGBoost outperformed other classifiers in accuracy

Sensitivity analysis revealed key features affecting model performance

Abstract

Applications of blockchain technologies got a lot of attention in recent years. They exceed beyond exchanging value and being a substitute for fiat money and traditional banking system. Nevertheless, being able to exchange value on a blockchain is at the core of the entire system and has to be reliable. Blockchains have built-in mechanisms that guarantee whole system's consistency and reliability. However, malicious actors can still try to steal money by applying well known techniques like malware software or fake emails. In this paper we apply supervised learning techniques to detect fraudulent accounts on Ethereum blockchain. We compare capabilities of Random Forests, Support Vector Machines and XGBoost classifiers to identify such accounts basing on a dataset of more than 300 thousands accounts. Results show that we are able to achieve recall and precision values allowing for the designed system to be applicable as an anti-fraud rule for digital wallets or currency exchanges. We also present sensitivity analysis to show how presented models depend on particular feature and how lack of some of them will affect the overall system performance.