Enhanced Credit Card Fraud Detection Using Deep Hybrid CLST Model
The existing financial payment system has inherent credit card fraud problems that must be solved with strong and effective solutions. In this research, a combined deep learning model that incorporates a convolutional neural network (CNN), long-short-term memory (LSTM), and fully connected output la...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/13/12/1950 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849431330149892096 |
|---|---|
| author | Madiha Jabeen Shabana Ramzan Ali Raza Norma Latif Fitriyani Muhammad Syafrudin Seung Won Lee |
| author_facet | Madiha Jabeen Shabana Ramzan Ali Raza Norma Latif Fitriyani Muhammad Syafrudin Seung Won Lee |
| author_sort | Madiha Jabeen |
| collection | DOAJ |
| description | The existing financial payment system has inherent credit card fraud problems that must be solved with strong and effective solutions. In this research, a combined deep learning model that incorporates a convolutional neural network (CNN), long-short-term memory (LSTM), and fully connected output layer is proposed to enhance the accuracy of fraud detection, particularly in addressing the class imbalance problem. A CNN is used for spatial features, LSTM for sequential information, and a fully connected output layer for final decision-making. Furthermore, SMOTE is used to balance the data and hyperparameter tuning is utilized to achieve the best model performance. In the case of hyperparameter tuning, the detection rate is greatly enhanced. High accuracy metrics are obtained by the proposed CNN-LSTM (CLST) model, with a recall of 83%, precision of 70%, F1-score of 76% for fraudulent transactions, and ROC-AUC of 0.9733. The proposed model’s performance is enhanced by hyperparameter optimization to a recall of 99%, precision of 83%, F1-score of 91% for fraudulent cases, and ROC-AUC of 0.9995, representing almost perfect fraud detection along with a low false negative rate. These results demonstrate that optimization of hyperparameters and layers is an effective way to enhance the performance of hybrid deep learning models for financial fraud detection. While prior studies have investigated hybrid structures, this study is distinguished by its introduction of an optimized of CNN and LSTM integration within a unified layer architecture. |
| format | Article |
| id | doaj-art-f4c709119dc445edbb2b95b17e4e94b4 |
| institution | Kabale University |
| issn | 2227-7390 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj-art-f4c709119dc445edbb2b95b17e4e94b42025-08-20T03:27:40ZengMDPI AGMathematics2227-73902025-06-011312195010.3390/math13121950Enhanced Credit Card Fraud Detection Using Deep Hybrid CLST ModelMadiha Jabeen0Shabana Ramzan1Ali Raza2Norma Latif Fitriyani3Muhammad Syafrudin4Seung Won Lee5Department of Computer Science & IT, The Govt. Sadiq College Women University, Bahawalpur 63100, PakistanDepartment of Computer Science & IT, The Govt. Sadiq College Women University, Bahawalpur 63100, PakistanDepartment of Precision Medicine, Sungkyunkwan University School of Medicine, Suwon 16419, Republic of KoreaDepartment of Artificial Intelligence and Data Science, Sejong University, Seoul 05006, Republic of KoreaDepartment of Artificial Intelligence and Data Science, Sejong University, Seoul 05006, Republic of KoreaDepartment of Precision Medicine, Sungkyunkwan University School of Medicine, Suwon 16419, Republic of KoreaThe existing financial payment system has inherent credit card fraud problems that must be solved with strong and effective solutions. In this research, a combined deep learning model that incorporates a convolutional neural network (CNN), long-short-term memory (LSTM), and fully connected output layer is proposed to enhance the accuracy of fraud detection, particularly in addressing the class imbalance problem. A CNN is used for spatial features, LSTM for sequential information, and a fully connected output layer for final decision-making. Furthermore, SMOTE is used to balance the data and hyperparameter tuning is utilized to achieve the best model performance. In the case of hyperparameter tuning, the detection rate is greatly enhanced. High accuracy metrics are obtained by the proposed CNN-LSTM (CLST) model, with a recall of 83%, precision of 70%, F1-score of 76% for fraudulent transactions, and ROC-AUC of 0.9733. The proposed model’s performance is enhanced by hyperparameter optimization to a recall of 99%, precision of 83%, F1-score of 91% for fraudulent cases, and ROC-AUC of 0.9995, representing almost perfect fraud detection along with a low false negative rate. These results demonstrate that optimization of hyperparameters and layers is an effective way to enhance the performance of hybrid deep learning models for financial fraud detection. While prior studies have investigated hybrid structures, this study is distinguished by its introduction of an optimized of CNN and LSTM integration within a unified layer architecture.https://www.mdpi.com/2227-7390/13/12/1950credit card frauddeep learningmachine learningSMOTECNNLSTM |
| spellingShingle | Madiha Jabeen Shabana Ramzan Ali Raza Norma Latif Fitriyani Muhammad Syafrudin Seung Won Lee Enhanced Credit Card Fraud Detection Using Deep Hybrid CLST Model Mathematics credit card fraud deep learning machine learning SMOTE CNN LSTM |
| title | Enhanced Credit Card Fraud Detection Using Deep Hybrid CLST Model |
| title_full | Enhanced Credit Card Fraud Detection Using Deep Hybrid CLST Model |
| title_fullStr | Enhanced Credit Card Fraud Detection Using Deep Hybrid CLST Model |
| title_full_unstemmed | Enhanced Credit Card Fraud Detection Using Deep Hybrid CLST Model |
| title_short | Enhanced Credit Card Fraud Detection Using Deep Hybrid CLST Model |
| title_sort | enhanced credit card fraud detection using deep hybrid clst model |
| topic | credit card fraud deep learning machine learning SMOTE CNN LSTM |
| url | https://www.mdpi.com/2227-7390/13/12/1950 |
| work_keys_str_mv | AT madihajabeen enhancedcreditcardfrauddetectionusingdeephybridclstmodel AT shabanaramzan enhancedcreditcardfrauddetectionusingdeephybridclstmodel AT aliraza enhancedcreditcardfrauddetectionusingdeephybridclstmodel AT normalatiffitriyani enhancedcreditcardfrauddetectionusingdeephybridclstmodel AT muhammadsyafrudin enhancedcreditcardfrauddetectionusingdeephybridclstmodel AT seungwonlee enhancedcreditcardfrauddetectionusingdeephybridclstmodel |