Enhancing Cryptocurrency Fraud Detection with Hybrid Feature-Graph Learning

Abstract

We introduce a hybrid system for detecting suspicious blockchain transactions, blending explainable machine learning (like Random Forest) with neural networks to analyze both raw transaction details and network patterns. Our approach achieves industry-leading accuracy (92% F1-score), solving two critical flaws in existing tools: 1) It cuts redundant data noise by 64% using smart feature filtering, and 2) uncovers hidden money trails through transaction graph analysis. While effective, current limitations include reliance on historical data—making it vulnerable to evolving scams like manipulated transaction networks in DeFi schemes—and slower processing times (32 training cycles) that challenge real-time monitoring on high-speed networks like Ethereum. Planned upgrades include dynamic AI models that adapt to live transaction flows and efficient detection systems for time-sensitive environments. We’re also developing stress tests using simulated cyberattack patterns and privacy-focused collaborative training across blockchain nodes. By merging technical precision with clear audit trails, this framework helps financial investigators spot risks like dark market ties while meeting strict compliance standards, offering a practical solution to balance speed and detection accuracy in crypto markets.