MACHINE LEARNING APPROACH TO ETHEREUM FRAUD DETECTION: COMPARATIVE ANALYSIS OF LOGISTIC REGRESSION AND RANDOM FOREST
DOI:
https://doi.org/10.15282/Keywords:
Ethereum Fraud Detection, Blockchain Security, Machine Learning, Random Forest, Logistic RegressionAbstract
Since its inception, the pseudonymous and decentralised nature of Ethereum has made it challenging to trace fraud. The fraud type identified is the fraudulent reuse of the same funds from copied unique received addresses and a different time between the first and last user transactions. This study compares and examines the performance of Logistic Regression and Random Forest models in detecting unusual Ethereum transactions and finding the most significant features influencing these outcomes. Traditional approaches tend to overlook lightweight, interpretable models that may be utilised for real-time filtering or focus on Bitcoin rather than Ethereum. To fill this gap, this study utilises machine learning to detect meaningful patterns of behaviour related to fraud. This study compares the performance of Random Forest and Logistic Regression models in classifying fraudulent Ethereum transactions. The dataset was extracted from a publicly available repository called Ethereum Fraud Detection. The dataset was normalised and cleaned using MinMaxScaler and then split into 80% training and 20% testing subsets. Feature scaling, correlation analysis, and removal of duplicate variables (such as ERC20 tokens) were part of the pre-processing. With 90.40% accuracy and an F1-score of 89.17%, the model suggests that Random Forest is a better performer than Logistic Regression. The ability of the model to identify non-fraud instances is clear from the visualisation of the confusion matrix, which also identifies areas for improvement in identifying actual fraud cases. These results provide business organisations with actionable recommendations on how to deploy real-time detection, rank high-risk transaction signals, and utilise adaptive machine learning architectures. This study promotes further research into anomaly detection based on deep learning and demonstrates the potential of feature-based machine learning in bolstering the Ethereum security infrastructure.
Downloads
References
[1] Ethereum.org, “What is Ethereum?,” 2025. [Online]. Available: https://ethereum.org/en/what-is-ethereum/. Accessed: Feb. 28, 2025.
[2] Q. Huang, “Ethereum: Introduction, expectation, and implementation,” Highlights in Science, Engineering and Technology, vol. 39, pp. 1–7, 2023, https://doi.org/10.54097/hset.v39i.6188
[3] A. Belanger, “MIT students stole $25M in seconds by exploiting ETH blockchain bug, DOJ says,” Ars Technica, May 16, 2024. [Online]. Available: https://arstechnica.com/tech-policy/2024/05/sophisticated-25m-ethereum-heist-took-about-12-seconds-doj-says/. Accessed: Feb. 28, 2025.
[4] C. Isidore, “Two former MIT students charged with stealing $25 million of crypto in 12 seconds,” CNN Business, May 16, 2024. [Online]. Available: https://edition.cnn.com/2024/05/16/investing/mit-crypto-hack/index.html. Accessed: Feb. 28, 2025.
[5] European Parliament and Council of the European Union, “Regulation (EU) 2023/1114 of the European Parliament and of the Council on markets in crypto-assets (MiCA),” Official Journal of the European Union, 2023. [Online]. Available: https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=CELEX:32023R1114. Accessed: Feb. 28, 2025.
[6] Y. Elmougy and O. Manzi, “Anomaly detection on Bitcoin, Ethereum networks using GPU-accelerated machine learning methods,” in Proceedings of the 31st International Conference on Computer Theory and Applications (ICCTA), Alexandria, Egypt, 2021, pp. 166–171, https://doi.org/10.1109/ICCTA54562.2021.9916625
[7] I. J. Onu, A. E. Omolara, M. Alawida, O. I. Abiodun, and A. Alabdultif, “Detection of Ponzi scheme on Ethereum using machine learning algorithms,” Scientific Reports, vol. 13, Art. no. 18403, 2023, https://doi.org/10.1038/s41598-023-45275-0
[8] C. G. Koa, S. H. Heng, and J. J. Chin, “New Ethereum-based distributed PKI with a reward-and-punishment mechanism,” Blockchain: Research and Applications, vol. 6, no. 1, Art. no. 100239, 2025, https://doi.org/10.1016/j.bcra.2024.100239
[9] S. Siddamsetti and M. Srivenkatesh, “Efficient fraud detection in Ethereum blockchain through machine learning and deep learning approaches,” International Journal on Recent and Innovation Trends in Computing and Communication, vol. 11, no. 11s, pp. 71–82, 2023, https://doi.org/10.17762/ijritcc.v11i11s.8072
[10] V. Aliyev, “Ethereum fraud detection dataset,” Kaggle, 2021. [Online]. Available: https://www.kaggle.com/datasets/vagifa/ethereum-frauddetection-dataset. Accessed: Feb. 28, 2025.
[11] M. L. Zeng and J. Qin, Metadata, 3rd ed. Chicago, IL, USA: ALA Neal-Schuman, 2022. ISBN: 978-0-8389-4875-5.
[12] T. Ashfaq, R. Khalid, A. S. Yahaya, et al., “A machine learning and blockchain based efficient fraud detection mechanism,” Sensors, vol. 22, no. 19, Art. no. 7162, 2022, https://doi.org/10.3390/s22197162
[13] P. Azad, C. G. Akcora, and A. Khan, “Machine learning for blockchain data analysis: Progress and opportunities,” Distributed Ledger Technologies: Research and Practice, vol. 5, no. 1, Art. no. 10, 2026, https://doi.org/10.1145/3728474
[14] Apache Software Foundation, “PySpark overview,” Apache Spark. [Online]. Available: https://spark.apache.org/docs/latest/api/python/index.html. Accessed: Feb. 28, 2025.
[15] I. G. T. Isa, Z. Zulkarnaini, L. Novianti, F. Elfaladonna, and S. Agustri, “Exploratory data analysis (EDA) dalam dataset penerimaan mahasiswa baru Universitas XYZ Palembang” [Exploratory data analysis (EDA) on the new-student admission dataset of University XYZ Palembang], Smart Comp: Jurnalnya Orang Pintar Komputer, vol. 12, no. 3, pp. 600–609, 2023, https://doi.org/10.30591/smartcomp.v12i3.4125
[16] S. Jiang, J. Josse, and M. Lavielle, “Logistic regression with missing covariates—Parameter estimation, model selection and prediction within a joint-modeling framework,” Computational Statistics & Data Analysis, vol. 145, Art. no. 106907, 2020, https://doi.org/10.1016/j.csda.2019.106907
[17] Z. Gu and O. Dib, “Enhancing fraud detection in the Ethereum blockchain using ensemble learning,” PeerJ Computer Science, vol. 11, Art. no. e2716, 2025, https://doi.org/10.7717/peerj-cs.2716
[18] R. M. Aziz, M. F. Baluch, S. Patel, and A. H. Ganie, “LGBM: A machine learning approach for Ethereum fraud detection,” International Journal of Information Technology, vol. 14, no. 7, pp. 3321–3331, 2022, https://doi.org/10.1007/s41870-022-00864-6
[19] C. Kaope and Y. Pristyanto, “The effect of class imbalance handling on datasets toward classification algorithm performance,” MATRIK: Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer, vol. 22, no. 2, pp. 227–238, 2023, https://doi.org/10.30812/matrik.v22i2.2515
[20] O. Mounnan, O. Manad, L. Boubchir, A. El Mouatasim, and B. Daachi, “A review on deep anomaly detection in blockchain,” Blockchain: Research and Applications, vol. 5, no. 4, Art. no. 100227, 2024, https://doi.org/10.1016/j.bcra.2024.100227
[21] J. Chen, X. Wang, and F. Lei, “Data-driven multinomial random forest: A new random forest variant with strong consistency,” Journal of Big Data, vol. 11, Art. no. 34, 2024, https://doi.org/10.1186/s40537-023-00874-6
Downloads
Published
Issue
Section
License
Copyright (c) 2026 The Author(s)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
