Ponzi Scheme Detection and Identification in Cryptocurrency-Based Scams using Machine Learning Techniques

Vishal Sharma; Dr. Ankush Shrivastava

doi:10.71097/IJSAT.v17.i2.11233

Ponzi Scheme Detection and Identification in Cryptocurrency-Based Scams using Machine Learning Techniques

Author(s)	Vishal Sharma, Dr. Ankush Shrivastava
Country	India
Abstract	The rapid expansion of cryptocurrency markets has provided fertile ground for financial fraud, particularly Ponzi schemes that promise high returns to early investors using funds from later participants. The pseudonymous and decentralized nature of blockchain transactions makes manual detection infeasible at scale. This research work proposes a machine learning (ML) framework for automated detection and identification of Ponzi schemes in cryptocurrency networks. The complete transaction ecosystem is modeled as a directed temporal graph and extracts some structural and dynamic features, which include transaction velocity, early flow ratio, burstiness, and network centrality. An XGBoost ensemble classifier is trained on a simulated dataset (5% Ponzi, 95% normal) and achieves an accuracy of 98.1%, a precision of 96.3%, a recall of 95.7%, an F_1-score of 96.0%, and an AUC-ROC of 99.4%, which outperforms random forest, SVM, and logistic regression baselines. The SHAP analysis identifies transaction velocity and early flow ratio as the most influential features. The proposed framework offers an interpretable, scalable, and highly accurate solution for real-time cryptocurrency fraud monitoring, with potential integration into blockchain surveillance systems.
Keywords	Ponzi Scheme Detection, Cryptocurrency Fraud, Machine Learning, XGBoost, Blockchain Forensics, Transaction Graph Analysis, SHAP Interpretability, Ethereum, Bitcoin.
Field	Engineering
Published In	Volume 17, Issue 2, April-June 2026
Published On	2026-06-01
DOI	https://doi.org/10.71097/IJSAT.v17.i2.11233

View / Download PDF File

About IJSAT Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	Message on WhatsApp	+91-9687-182-185	editor@ijsat.org

International Journal on Science and Technology

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Ponzi Scheme Detection and Identification in Cryptocurrency-Based Scams using Machine Learning Techniques

Share this