EnLEFD‐DM: Ensemble Learning based Ethereum Fraud Detection using CRISP‐DM framework

Abstract

AbstractCryptocurrencies continue to captivate businesses and investors despite market fluctuations. The number of crypto users has risen rapidly in the last few years, and alarmingly, many appear to be unaware of the risks involved. These risks aren't confined to market hazards but include very sophisticated cybercrimes related to cryptocurrencies. As cryptocurrencies have become a breeding ground for a variety of cybercrimes, resulting in enormous financial losses, it hinders user adoption limiting the utility of blockchain technology. It has become crucial to spot such scams and devise intelligent techniques to make this technology safer for investors. This paper proposes a classification model based on the Cross Industry Standard Process for Data Mining (CRISP‐DM) framework to identify fraudulent transactions over the Ethereum blockchain. Its contribution is multi‐faceted; first, the available imbalanced Ethereum dataset has been balanced to enhance the accuracy of the classification model. Second, the correlation‐based feature selection technique has been applied to retain the best discriminating features. Thirdly, an effective machine learning‐based ensemble classification model has been adopted for the identification of fraudulent transactions over the Ethereum network. A comparative analysis of 10 machine learning techniques has been presented consisting of both individual and ensemble classifiers. Evaluated outcomes show that ensemble classifiers appear to yield better performance measures over individual classifiers, and among all, the LightGbm classifier outperformed with 99.2% accuracy. Further, extensive experiments indicate that the proposed method outperforms the state‐of‐the‐art method when applied to a similar dataset.