Research on Financial Fraud Identification System Based on Differential Privacy

Authors

  • Sijia Shen
  • Yueling Li

DOI:

https://doi.org/10.54097/jceim.v10i1.5335

Keywords:

Fraud Detection, Isolated Data Island, Optimal Subsampling, Differential Privacy

Abstract

 Data sharing among financial institutions is often not possible, resulting in a "data silo" situation. In this paper, we train an efficient financial fraud detection model under the framework of privacy protection from the perspective of facilitating the collaboration of multiple financial institutions to train a fraud identification system. This paper first used traditional oversampling and under sampling methods to balance the data and train models such as logistic regression, support vector machines and random forests, but did not obtain the desired results. In contrast, the optimal subsampling method based on logistic regression performs well in terms of training results and program runtime. To protect data security, differential privacy is introduced on this basis to find the classification accuracy of the model under different privacy budgets. It is concluded that a certain balance between the degree of privacy protection and model effectiveness should be achieved according to privacy requirements.

References

Chawla N V, Bowyer K W, Hall L O, et al. SMOTE: Synthetic Minority Oversampling Technique[J]. Journal of Artificial Intelligence Research, 2002, 16(1):321-357.

Guo Haixiang, Li Yijing, Jennifer Shang, Gu Mingyun, Huang Yuanyue, and Gong Bing. Learning from class-imbalanced data: Review of methods and applications[J]. Expert Systems with Applications, 2017,73:220–239.

Elreedy D, Atiya A F. A Comprehensive Analysis of Synthetic Minority Oversampling Technique (SMOTE) for handling class imbalance - ScienceDirect[J]. Information Sciences, 2019, 505:32-64.

Wang H, Zhu R, Ping M. Optimal Subsampling for Large Sample Logistic Regression[J]. Journal of the American Statistical Association, 2017, 113(2):1440037-1438957.

Dwork C. Calibrating noise to sensitivity in private data analysis[J]. Lecture Notes in Computer Science,2012,3876(8):265-284.

Zhang J , Zhang Z , Xiao X , et al. Functional Mechanism: Regression Analysis under Differential Privacy[J]. Proceedings of the VLDB Endowment, 2012, 5(11):1364-1375.

Kurz Christoph. Understanding differential privacy[J]. Significance, 2021, 18(3):24-27.

Samet S. Privacy-preserving logistic regression[J]. Journal of Advances in Information Technology,2015,6(3):1–8.

Alonso E, Elmir A, Axelsson S. Paysim: a financial mobile money simulator for fraud detection[C]// European Modeling & Simulation Symposium. 2016.

Downloads

Published

20-02-2023

Issue

Section

Articles

How to Cite

Shen, S., & Li, Y. (2023). Research on Financial Fraud Identification System Based on Differential Privacy. Journal of Computing and Electronic Information Management, 10(1), 28-31. https://doi.org/10.54097/jceim.v10i1.5335

Similar Articles

1-10 of 77

You may also start an advanced similarity search for this article.