Analyzing Various Machine Learning Algorithms for Blockchain-Based Fraud Detection

Authors

  • S Giribabu Assistant Professor, Department of Computer Science & Engineering, PACE Institute of Technology and Sciences, Ongole, Andhra Pradesh, India Author
  • V Sriharsha Assistant Professor, Department of Computer Science & Engineering, PACE Institute of Technology and Sciences, Ongole, Andhra Pradesh, India Author
  • Patan Hussain Basha Assistant Professor, Department of Computer Science & Engineering, PACE Institute of Technology and Sciences, Ongole, Andhra Pradesh, India Author
  • K Suresh Assistant Professor, Department of Computer Science & Engineering, PACE Institute of Technology and Sciences, Ongole, Andhra Pradesh, India Author
  • M Sivudu Assistant Professor, Department of Computer Science & Engineering, PACE Institute of Technology and Sciences, Ongole, Andhra Pradesh, India Author

DOI:

https://doi.org/10.55524/

Keywords:

Blockchain, Machine, Learning, Machine Learning Algorithms, Fraud Detection

Abstract

A blockchain network's economics and  user confidence can be seriously harmed by fraud. Consensus algorithms like proof of work and proof of  stake can verify the legitimacy of a transaction but not the  identity of the people who are conducting or verifying it. On a blockchain network, fraud can still occur, as a result  of this. One approach to fighting fraud is to make use of  machine learning techniques. There are two types of  machine learning: supervised and unsupervised. We use a  variety of supervised machine learning techniques in this  study to distinguish between legitimate and fraudulent  purchases. We also compare decision trees, Naive Bayes,  logistic regression, multilayer perceptron, and other  supervised machine learning techniques in detail for this  challenge. 

Downloads

Download data is not yet available.

References

Cai, Y., Zhu, D. Fraud detections for online businesses: a perspectivefrom blockchain technology.

Xu, J.J. Are blockchains immune to all malicious attacks [3] Ostapowicz M., ˙ Zbikowski K. (2019) Detecting Fraudulent Accounts on Blockchain: A Supervised Approach

Podgorelec, B., Turkanovi´c, M. and Karakatiˇc, S., 2020. A Machine Learning-Based Method for Automated Blockchain Transaction Signing Including Personalized Anomaly Detection.

Farrugia S, Ellul J, Azzopardi G. Detection of illicit accounts over the Ethereum blockchain. Expert Systems

with Applications

Pham, Thai, and Steven Lee. ”Anomaly detection in bitcoin network using unsupervised learning methods [7] Li, Ji, et al. ”A Survey on Blockchain Anomaly Detection UsingData Mining Techniques.

Brenig, Christian, and G¨unterM¨uller. ”Economic analysis of cryptocurrency backed money laundering.” (2015) [9] Monamo, Patrick, VukosiMarivate, and Bheki Twala. ”Unsupervised learning for robust Bitcoin fraud detection.” 2016 Information Security for South Africa (ISSA). IEEE, 2016.

Anomaly Detection in Bitcoin Network Using Unsupervised Learning Methods

Data mining for credit card fraud: A comparative study S. Bhattacharyya, Sanjeev Jha, K. Tharakunnel, J. Westland [12] The application of data mining techniques in financial fraud detection: A classification framework and an academic review of literature E. Ngai, Yong Hu, Y. Wong, Yijun Chen, Xin Sun

Graph based anomaly detection and description: a survey L. Akoglu, Hanghang Tong, Danai Koutra.

Downloads

Published

2022-05-30

Issue

Vol. 10 No. 3 (2022): International Journal of Innovative Research in Computer Science and Technology (May )2022

Section

Articles

How to Cite

Analyzing Various Machine Learning Algorithms for Blockchain-Based Fraud Detection . (2022). International Journal of Innovative Research in Computer Science & Technology, 10(3), 375–380. https://doi.org/10.55524/
Crossref
Scopus
Google Scholar
Europe PMC