—The surge in cryptocurrency adoption has redefined digital finance, introducing decentralization and transparency but also facilitating illicit activities such as drug trafficking and money laundering. The pseudonymous nature of digital assets like Bitcoin, Ethereum, and Monero poses major challenges for law-enforcement agencies in tracing the real identities behind suspicious wallet activities. This research proposes CryptoMapAI, an AI-driven framework designed to trace cryptocurrency transactions to their final destinations and uncover hidden criminal networks. The system integrates blockchain data from public and privacy-centric networks with external intelligence sources including darknet markets and flagged wallet databases. Using machine learning, graph analytics, and recursive clustering, CryptoMapAI identifies obfuscated transaction flows across mixers, tumblers, and cross-chain transfers. The model employs Random Forest and anomaly detection algorithms to classify suspicious activities and visualize the complete transaction network through an intuitive dashboard. Experimental results demonstrate a detection accuracy of 99%, enabling efficient identification of high-risk wallets and transaction patterns.
Rushikesh Tokle (Thu,) studied this question.