CTCN: a novel credit card fraud detection method based on Conditional Tabular Generative Adversarial Networks and Temporal Convolutional Network
Credit card fraud can lead to significant financial losses for both individuals and financial institutions. In this article, we propose a novel method called CTCN, which uses Conditional Tabular Generative Adversarial Networks (CTGAN) and temporal convolutional network (TCN) for credit card fraud de...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2023-10-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-1634.pdf |
| _version_ | 1797660941193576448 |
|---|---|
| author | Xiaoyan Zhao Shaopeng Guan |
| author_facet | Xiaoyan Zhao Shaopeng Guan |
| author_sort | Xiaoyan Zhao |
| collection | DOAJ |
| description | Credit card fraud can lead to significant financial losses for both individuals and financial institutions. In this article, we propose a novel method called CTCN, which uses Conditional Tabular Generative Adversarial Networks (CTGAN) and temporal convolutional network (TCN) for credit card fraud detection. Our approach includes an oversampling algorithm that uses CTGAN to balance the dataset, and Neighborhood Cleaning Rule (NCL) to filter out majority class samples that overlap with the minority class. We generate synthetic minority class samples that conform to the original data distribution, resulting in a balanced dataset. We then employ TCN to analyze transaction sequences and capture long-term dependencies between data, revealing potential relationships between transaction sequences, thus achieving accurate credit card fraud detection. Experiments on three public datasets demonstrate that our proposed method outperforms current machine learning and deep learning methods, as measured by recall, F1-Score, and AUC-ROC. |
| first_indexed | 2024-03-11T18:38:09Z |
| format | Article |
| id | doaj.art-bae209b6103244f98508e60bcb0dbc7a |
| institution | Directory Open Access Journal |
| issn | 2376-5992 |
| language | English |
| last_indexed | 2024-03-11T18:38:09Z |
| publishDate | 2023-10-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj.art-bae209b6103244f98508e60bcb0dbc7a2023-10-12T15:05:16ZengPeerJ Inc.PeerJ Computer Science2376-59922023-10-019e163410.7717/peerj-cs.1634CTCN: a novel credit card fraud detection method based on Conditional Tabular Generative Adversarial Networks and Temporal Convolutional NetworkXiaoyan Zhao0Shaopeng Guan1School of Information and Electronic Engineering, Shandong Technology and Business University, Yantai, ChinaSchool of Information and Electronic Engineering, Shandong Technology and Business University, Yantai, ChinaCredit card fraud can lead to significant financial losses for both individuals and financial institutions. In this article, we propose a novel method called CTCN, which uses Conditional Tabular Generative Adversarial Networks (CTGAN) and temporal convolutional network (TCN) for credit card fraud detection. Our approach includes an oversampling algorithm that uses CTGAN to balance the dataset, and Neighborhood Cleaning Rule (NCL) to filter out majority class samples that overlap with the minority class. We generate synthetic minority class samples that conform to the original data distribution, resulting in a balanced dataset. We then employ TCN to analyze transaction sequences and capture long-term dependencies between data, revealing potential relationships between transaction sequences, thus achieving accurate credit card fraud detection. Experiments on three public datasets demonstrate that our proposed method outperforms current machine learning and deep learning methods, as measured by recall, F1-Score, and AUC-ROC.https://peerj.com/articles/cs-1634.pdfCredit card fraud detectionNeighborhood cleaning ruleConditional tabular generative adversarial networkTemporal convolutional network |
| spellingShingle | Xiaoyan Zhao Shaopeng Guan CTCN: a novel credit card fraud detection method based on Conditional Tabular Generative Adversarial Networks and Temporal Convolutional Network PeerJ Computer Science Credit card fraud detection Neighborhood cleaning rule Conditional tabular generative adversarial network Temporal convolutional network |
| title | CTCN: a novel credit card fraud detection method based on Conditional Tabular Generative Adversarial Networks and Temporal Convolutional Network |
| title_full | CTCN: a novel credit card fraud detection method based on Conditional Tabular Generative Adversarial Networks and Temporal Convolutional Network |
| title_fullStr | CTCN: a novel credit card fraud detection method based on Conditional Tabular Generative Adversarial Networks and Temporal Convolutional Network |
| title_full_unstemmed | CTCN: a novel credit card fraud detection method based on Conditional Tabular Generative Adversarial Networks and Temporal Convolutional Network |
| title_short | CTCN: a novel credit card fraud detection method based on Conditional Tabular Generative Adversarial Networks and Temporal Convolutional Network |
| title_sort | ctcn a novel credit card fraud detection method based on conditional tabular generative adversarial networks and temporal convolutional network |
| topic | Credit card fraud detection Neighborhood cleaning rule Conditional tabular generative adversarial network Temporal convolutional network |
| url | https://peerj.com/articles/cs-1634.pdf |
| work_keys_str_mv | AT xiaoyanzhao ctcnanovelcreditcardfrauddetectionmethodbasedonconditionaltabulargenerativeadversarialnetworksandtemporalconvolutionalnetwork AT shaopengguan ctcnanovelcreditcardfrauddetectionmethodbasedonconditionaltabulargenerativeadversarialnetworksandtemporalconvolutionalnetwork |