well in distinguishing in the range of positive and
negative samples. The AUC value of 0.999, which
tends to 1, indicates that the model has excellent
classification performance. As the rate of false
positive cases increases, the rate of true cases also
increases significantly, indicating that the model can
effectively recognize positive samples.
4.4 Model Comparisons
Comparing the total prediction precision of the
model, predictive accuracy of class 0 and class 1
respectively, the recall rate, and the F1 score, the
following conclusions can be drawn that the XGB
Classifier model has a higher degree of classification
accuracy and a relatively low misclassification rate,
which makes it more suitable for handling this task.
5 CONCLUSIONS
Fraud detection on blockchain platforms like
Ethereum is of paramount importance due to the
increasing prevalence of digital transactions. This
study evaluated the effectiveness of logistic
regression, random forest, and XGBoost classifiers in
identifying fraudulent activities within Ethereum
transaction data. Through rigorous model training and
testing, it was found that both the random forest and
XGBoost models provided robust performance, with
each model demonstrating unique strengths. These
findings underscore the value of tree-based models in
managing high-dimensional data and contribute to the
ongoing efforts to enhance fraud detection
mechanisms within the blockchain ecosystem.
Future study may investigate the incorporation of
more powerful machine learning algorithms, such as
deep learning, to further increase the accuracy and
efficiency of fraud detection. Additionally,
investigating the applicability of these models in real-
time fraud detection systems and their scalability
across different blockchain platforms could provide
valuable insights for practical implementation.
REFERENCES
Bhowmik, M., Chandana, T. S. S., & Rudra, B. (2021,
April). Comparative study of machine learning
algorithms for fraud detection in blockchain. In 2021
5th international conference on computing
methodologies and communication (ICCMC) (pp. 539-
541). IEEE.
Hu, S., Zhang, Z., Luo, B., Lu, S., He, B., & Liu, L. (2023,
April). Bert4eth: A pre-trained transformer for
ethereum fraud detection. In Proceedings of the ACM
Web Conference 2023 (pp. 2189-2197).
Jung, E., Le Tilly, M., Gehani, A., & Ge, Y. (2019, July).
Data mining-based ethereum fraud detection. In 2019
IEEE international conference on blockchain
(Blockchain) (pp. 266-273). IEEE.
K. A. R. A., & Aydos, M. (2020, October). Cyber fraud:
Detection and analysis of the crypto-ransomware. In
2020 11th IEEE Annual Ubiquitous Computing,
Electronics & Mobile Communication Conference
(UEMCON) (pp. 0764-0769). IEEE.
Nayyer, N., Javaid, N., Akbar, M., Aldegheishem, A.,
Alrajeh, N., & Jamil, M. (2023). A new framework for
fraud detection in bitcoin transactions through
ensemble stacking model in smart cities. IEEE Access.
Singh, A., Gupta, A., Wadhwa, H., Asthana, S., & Arora,
A. (2021, December). Temporal debiasing using
adversarial loss based GNN architecture for crypto
fraud detection. In 2021 20th IEEE International
Conference on Machine Learning and Applications
(ICMLA) (pp. 391-396). IEEE.
Saldamli, G., Reddy, V., Bojja, K. S., Gururaja, M. K.,
Doddaveerappa, Y., & Tawalbeh, L. (2020, April).
Health care insurance fraud detection using blockchain.
In 2020 seventh international conference on software
defined systems (SDS) (pp. 145-152). IEEE.
Shayegan, M. J., Sabor, H. R., Uddin, M., & Chen, C. L.
(2022). A collective anomaly detection technique to
detect crypto wallet frauds on bitcoin network.
Symmetry, 14(2), 328.
Tan, R., Tan, Q., Zhang, P., & Li, Z. (2021, December).
Graph neural network for ethereum fraud detection. In
2021 IEEE international conference on big knowledge
(ICBK) (pp. 78-85). IEEE.
Tan, R., Tan, Q., Zhang, Q., Zhang, P., Xie, Y., & Li, Z.
(2023). Ethereum fraud behavior detection based on
graph neural networks. Computing, 105(10), 2143-
2170.