Abstract :

Money Laundering Using Cryptocurrency Networks Poses An Escalating Challenge Owing To The Intrinsic Anonymity Of Blockchain Transactions. Layering Strategies Employed On Decentralized Platforms Conceal The Identities Of Senders And Receivers, Hence Complicating Compliance And Enforcement Efforts. A Dual-layered Strategy Integrating Machine Learning (ML) And Value-driven Transactional Tracking Analytics For Crypto-compliance (VTAC) Is Presented To Resolve This Issue. This System Facilitates Efficient De-anonymization And Categorization Of Criminal Transactions. The Machine Learning Component Encompasses Data Preprocessing, Standard Scaling Normalization, Model Training With Supervised Classifiers, And Hash Address Identification From Transaction Identifiers. VTAC Improves Detection Through The Analysis Of Transaction Frequency And Behavioral Irregularities. Three Foundational Classifiers—Random Forest, XGBoost, And AdaBoost—are Assessed. Additional Enhancements Are Implemented By A Hybrid Ensemble Of XGBoost And Random Forest, Along With Advanced Algorithms Such As LightGBM And CatBoost. Performance Is Evaluated By Accuracy, Precision, Recall, F1-score, And Confusion Matrix On The Elliptic Bitcoin Dataset. Results Indicate Enhanced Detection Rates Using LightGBM. A Web-based Interface Enables Real-time Prediction Of Unlawful Transactions, Hash Traceability, And Compliance Reporting. This Approach Enhances Blockchain Forensics And Regulatory Monitoring By Merging Analytics With Blockchain Infrastructure.

Published:

08-4-2026

Issue:

Vol. 26 No. 4 (2026)

Page Nos:

1732-1742

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite