Detection of Ponzi scheme on Ethereum using machine learning algorithms

Abstract

Security threats posed by Ponzi schemes present a considerably higher risk compared to many other online crimes. These fraudulent online businesses, including Ponzi schemes, have witnessed rapid growth and emerged as major threats in societies like Nigeria, particularly due to the high poverty rate. Many individuals have fallen victim to these scams, resulting in significant financial losses. Despite efforts to detect Ponzi schemes using various methods, including machine learning (ML), current techniques still face challenges, such as deficient datasets, reliance on transaction records, and limited accuracy. To address the negative impact of Ponzi schemes, this paper proposes a novel approach focusing on detecting Ponzi schemes on Ethereum using ML algorithms like random forest (RF), neural network (NN), and K-nearest neighbor (KNN). Over 20,000 datasets related to Ethereum transaction networks were gathered from Kaggle and preprocessed for training the ML models. After evaluating and comparing the three models, RF demonstrated the best performance with an accuracy of 0.94, a class-score of 0.8833, and an overall-score of 0.96667. Comparative evaluations with previous models indicate that our model achieves high accuracy. Moreover, this innovative work successfully detects key fraud features within the Ponzi scheme dataset, reducing the number of features from 70 to only 10 while maintaining a high level of accuracy. The main strength of this proposed method lies in its ability to detect clever Ponzi schemes from their inception, offering valuable insights to combat these financial threats effectively.

Cryptocurrency fraud detection through classification techniques

“…In the context of binary classification algorithms, such as those employed to identify fraud or Ponzi schemes, the words true positive (TP), true negative (TN), false positive (FP), and false negative (FN) are frequently used. The terms "TP" and "TN" denote the quantity of Ponzi scheme contracts that are accurately detected and the quantity of contracts that are not Ponzi schemes, FP for the quantity of smart indentures that do not include Ponzi schemes but are mistakenly identified, and FN for the quantity of contracts involving Ponzi outlines that are mistakenly estimated as non-Ponzi outline indentures [24]. These are the definitions of precision, recall, and F1-Score, which we use to determine the model's performance: In comparison to the other models, the XGB classifier yields higher results in terms of accuracy.…”

Modeling the Dynamic Behaviors of Bank Account Fraudsters Using Combined Simultaneous Game Theory with Neural Networks

“…The study [29] uses a graph neural network in fraud detection in the supply chain, the authors were able to capture heterogeneous information. Financial fraud detection in cryptocurrency is discussed [30][31][32], and a collection of attributes that were taken from Ethereum is assessed using Neural Networks and Extreme Gradient Boosting [30]. A study [10,11] utilizes RF, LGBM, and MLP to detect fraud in Ethereum in cryptocurrency, LGBM and SVM outperform other methods in terms of accuracy, high FPR is a major setback.…”