Improving the Data Quality for Credit Card Fraud Detection

Rongrong Jing, Hu Xian, Yidi Li, Xingwei Zhang, Xiaolong Zheng, Zhu Zhang, Daniel Zeng

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Label imbalance and data missing are two major challenges in the problem of credit card fraud detection. However, existing matrix completion algorithms are generally difficult and cannot be easily applied to real-world credit card fraud detection since the scale of the normally used dataset is oversized. In this paper, we develop a spectral regularization algorithm to complete the large-scale sparse matrices, and further utilize an over-sampling algorithm to tackle the problem of the imbalance between positive and negative samples. Experimental results on a real-world dataset demonstrate that our model can outperform the state-of-the-art baseline methods. The proposed method could also be extended to other large-scale scenarios where data is missing or labels are imbalanced.

Original languageEnglish (US)
Title of host publicationProceedings - 2020 IEEE International Conference on Intelligence and Security Informatics, ISI 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728188003
DOIs
StatePublished - Nov 9 2020
Externally publishedYes
Event18th IEEE International Conference on Intelligence and Security Informatics, ISI 2020 - Virtual, Arlington, United States
Duration: Nov 9 2020Nov 10 2020

Publication series

NameProceedings - 2020 IEEE International Conference on Intelligence and Security Informatics, ISI 2020

Conference

Conference18th IEEE International Conference on Intelligence and Security Informatics, ISI 2020
Country/TerritoryUnited States
CityVirtual, Arlington
Period11/9/2011/10/20

Keywords

  • Credit card fraud Detection
  • Imbalanced data
  • Sparse matrix completion

ASJC Scopus subject areas

  • Information Systems and Management
  • Safety, Risk, Reliability and Quality
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Information Systems

Fingerprint

Dive into the research topics of 'Improving the Data Quality for Credit Card Fraud Detection'. Together they form a unique fingerprint.

Cite this