Generative Modeling for Imbalanced Credit Card Fraud Transaction Detection
The increasing sophistication of fraud tactics necessitates advanced detection methods to protect financial assets and maintain system integrity. Various approaches based on artificial intelligence have been proposed to identify fraudulent activities, leveraging techniques such as machine learning a...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Journal of Cybersecurity and Privacy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2624-800X/5/1/9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850279494376488960 |
|---|---|
| author | Mohammed Tayebi Said El Kafhali |
| author_facet | Mohammed Tayebi Said El Kafhali |
| author_sort | Mohammed Tayebi |
| collection | DOAJ |
| description | The increasing sophistication of fraud tactics necessitates advanced detection methods to protect financial assets and maintain system integrity. Various approaches based on artificial intelligence have been proposed to identify fraudulent activities, leveraging techniques such as machine learning and deep learning. However, class imbalance remains a significant challenge. We propose several solutions based on advanced generative modeling techniques to address the challenges posed by class imbalance in fraud detection. Class imbalance often hinders the performance of machine learning models by limiting their ability to learn from minority classes, such as fraudulent transactions. Generative models offer a promising approach to mitigate this issue by creating realistic synthetic samples, thereby enhancing the model’s ability to detect rare fraudulent cases. In this study, we introduce and evaluate multiple generative models, including Variational Autoencoders (VAEs), standard Autoencoders (AEs), Generative Adversarial Networks (GANs), and a hybrid Autoencoder–GAN model (AE-GAN). These models aim to generate synthetic fraudulent samples to balance the dataset and improve the model’s learning capacity. Our primary objective is to compare the performance of these generative models against traditional oversampling techniques, such as SMOTE and ADASYN, in the context of fraud detection. We conducted extensive experiments using a real-world credit card dataset to evaluate the effectiveness of our proposed solutions. The results, measured using the BEFS metrics, demonstrate that our generative models not only address the class imbalance problem more effectively but also outperform conventional oversampling methods in identifying fraudulent transactions. |
| format | Article |
| id | doaj-art-04286da702694a6fa43798d80f8a7ecf |
| institution | OA Journals |
| issn | 2624-800X |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Cybersecurity and Privacy |
| spelling | doaj-art-04286da702694a6fa43798d80f8a7ecf2025-08-20T01:49:04ZengMDPI AGJournal of Cybersecurity and Privacy2624-800X2025-03-0151910.3390/jcp5010009Generative Modeling for Imbalanced Credit Card Fraud Transaction DetectionMohammed Tayebi0Said El Kafhali1Computer, Networks, Modeling, and Mobility Laboratory (IR2M), Faculty of Sciences and Techniques, Hassan First University of Settat, Settat 26000, MoroccoComputer, Networks, Modeling, and Mobility Laboratory (IR2M), Faculty of Sciences and Techniques, Hassan First University of Settat, Settat 26000, MoroccoThe increasing sophistication of fraud tactics necessitates advanced detection methods to protect financial assets and maintain system integrity. Various approaches based on artificial intelligence have been proposed to identify fraudulent activities, leveraging techniques such as machine learning and deep learning. However, class imbalance remains a significant challenge. We propose several solutions based on advanced generative modeling techniques to address the challenges posed by class imbalance in fraud detection. Class imbalance often hinders the performance of machine learning models by limiting their ability to learn from minority classes, such as fraudulent transactions. Generative models offer a promising approach to mitigate this issue by creating realistic synthetic samples, thereby enhancing the model’s ability to detect rare fraudulent cases. In this study, we introduce and evaluate multiple generative models, including Variational Autoencoders (VAEs), standard Autoencoders (AEs), Generative Adversarial Networks (GANs), and a hybrid Autoencoder–GAN model (AE-GAN). These models aim to generate synthetic fraudulent samples to balance the dataset and improve the model’s learning capacity. Our primary objective is to compare the performance of these generative models against traditional oversampling techniques, such as SMOTE and ADASYN, in the context of fraud detection. We conducted extensive experiments using a real-world credit card dataset to evaluate the effectiveness of our proposed solutions. The results, measured using the BEFS metrics, demonstrate that our generative models not only address the class imbalance problem more effectively but also outperform conventional oversampling methods in identifying fraudulent transactions.https://www.mdpi.com/2624-800X/5/1/9fraud detectiongenerative modelsvariational autoencodergenerative adversarial neural networkclass imbalanceautoencoder |
| spellingShingle | Mohammed Tayebi Said El Kafhali Generative Modeling for Imbalanced Credit Card Fraud Transaction Detection Journal of Cybersecurity and Privacy fraud detection generative models variational autoencoder generative adversarial neural network class imbalance autoencoder |
| title | Generative Modeling for Imbalanced Credit Card Fraud Transaction Detection |
| title_full | Generative Modeling for Imbalanced Credit Card Fraud Transaction Detection |
| title_fullStr | Generative Modeling for Imbalanced Credit Card Fraud Transaction Detection |
| title_full_unstemmed | Generative Modeling for Imbalanced Credit Card Fraud Transaction Detection |
| title_short | Generative Modeling for Imbalanced Credit Card Fraud Transaction Detection |
| title_sort | generative modeling for imbalanced credit card fraud transaction detection |
| topic | fraud detection generative models variational autoencoder generative adversarial neural network class imbalance autoencoder |
| url | https://www.mdpi.com/2624-800X/5/1/9 |
| work_keys_str_mv | AT mohammedtayebi generativemodelingforimbalancedcreditcardfraudtransactiondetection AT saidelkafhali generativemodelingforimbalancedcreditcardfraudtransactiondetection |