AI-Driven Unsupervised Framework for Detecting and Analyzing Anomalous Cryptocurrency Transactions Across Blockchain Networks Using Multi-Feature Analysis
Main Article Content
The rapid growth of cryptocurrency networks has increased the risk of fraudulent transactions, necessitating effective and scalable detection methods. This study presents an AI-driven framework for detecting anomalous transactions in cryptocurrency datasets using unsupervised learning techniques, specifically the Isolation Forest algorithm. A dataset of 50,000 transactions was analyzed, with 500 anomalies successfully identified based on multiple features including transaction amount, fees, sender and receiver addresses, mining pools, and currency type. The results show that anomalous transactions frequently exhibit extreme values and irregular patterns that are difficult to detect using traditional rule-based approaches. Multi-feature analysis enhances detection accuracy, enabling the prioritization of high-risk transactions for manual review or automated mitigation. These findings demonstrate that unsupervised AI methods provide a robust, adaptive, and scalable solution for proactive fraud detection in blockchain networks, with the potential to integrate deeper learning models for further improvement in detecting complex fraudulent behaviors.