Detecting Ponzi Schemes on Ethereum: Towards Healthier Blockchain Technology
Blockchain technology becomes increasingly popular. It also attracts scams, for example, Ponzi scheme, a classic fraud, has been found making a notable amount of money on Blockchain, which has a very negative impact. To help dealing with this issue, we propose an approach to detect Ponzi schemes on Blockchain by using data mining and machine learning methods. By verifying smart contracts on Ethereum, we first extract features from user accounts and operation codes of the smartcontracts and then build a classification model to detect latent Ponzi schemes implemented as smart contracts. Using the manually checked samples and XGBoost, a regression tree model based on extracted account features and code features is build. The experimental results indicate that the proposed model has high accurate and can be used to detect latent smart Ponzi schemes in practice. The most significance results are that using our extracted code features that are publicly accessible in any running contract, is enough to build a practical model for detecting Ponzi scheme contract at the moment of its creation. In addition, we estimate that there are more than 400 smart Ponzi schemes on Ethereum, which are far more than the previous estimation. Based on these results, we propose to build a uniform platform to evaluate and monitor every created smart contract for early warning of scams. You can use our data to reproduce the results according to our paper.