Enhancing Financial Fraud Detection through Addressing Class Imbalance Using Hybrid SMOTE-GAN Techniques
The class imbalance problem in finance fraud datasets often leads to biased prediction towards the nonfraud class, resulting in poor performance in the fraud class. This study explores the effects of utilizing the Synthetic Minority Oversampling TEchnique (SMOTE), a Generative Adversarial Network (G...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | International Journal of Financial Studies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7072/11/3/110 |
| _version_ | 1797672365338918912 |
|---|---|
| author | Patience Chew Yee Cheah Yue Yang Boon Giin Lee |
| author_facet | Patience Chew Yee Cheah Yue Yang Boon Giin Lee |
| author_sort | Patience Chew Yee Cheah |
| collection | DOAJ |
| description | The class imbalance problem in finance fraud datasets often leads to biased prediction towards the nonfraud class, resulting in poor performance in the fraud class. This study explores the effects of utilizing the Synthetic Minority Oversampling TEchnique (SMOTE), a Generative Adversarial Network (GAN), and their combinations to address the class imbalance issue. Their effectiveness was evaluated using a Feed-forward Neural Network (FNN), Convolutional Neural Network (CNN), and their hybrid (FNN+CNN). This study found that regardless of the data generation techniques applied, the classifier’s hyperparameters can affect classification performance. The comparisons of various data generation techniques demonstrated the effectiveness of the hybrid SMOTE and GAN, including SMOTified-GAN, SMOTE+GAN, and GANified-SMOTE, compared with SMOTE and GAN. The SMOTified-GAN and the proposed GANified-SMOTE were able to perform equally well across different amounts of generated fraud samples. |
| first_indexed | 2024-03-11T21:28:59Z |
| format | Article |
| id | doaj.art-8d7ce787a14b4988bdfc3ea7d149c26a |
| institution | Directory Open Access Journal |
| issn | 2227-7072 |
| language | English |
| last_indexed | 2024-03-11T21:28:59Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | International Journal of Financial Studies |
| spelling | doaj.art-8d7ce787a14b4988bdfc3ea7d149c26a2023-09-27T13:11:11ZengMDPI AGInternational Journal of Financial Studies2227-70722023-09-011111011010.3390/ijfs11030110Enhancing Financial Fraud Detection through Addressing Class Imbalance Using Hybrid SMOTE-GAN TechniquesPatience Chew Yee Cheah0Yue Yang1Boon Giin Lee2School of Computer Science, University of Nottingham Ningbo China, Ningbo 315100, ChinaSchool of Computer Science, University of Nottingham Ningbo China, Ningbo 315100, ChinaSchool of Computer Science, University of Nottingham Ningbo China, Ningbo 315100, ChinaThe class imbalance problem in finance fraud datasets often leads to biased prediction towards the nonfraud class, resulting in poor performance in the fraud class. This study explores the effects of utilizing the Synthetic Minority Oversampling TEchnique (SMOTE), a Generative Adversarial Network (GAN), and their combinations to address the class imbalance issue. Their effectiveness was evaluated using a Feed-forward Neural Network (FNN), Convolutional Neural Network (CNN), and their hybrid (FNN+CNN). This study found that regardless of the data generation techniques applied, the classifier’s hyperparameters can affect classification performance. The comparisons of various data generation techniques demonstrated the effectiveness of the hybrid SMOTE and GAN, including SMOTified-GAN, SMOTE+GAN, and GANified-SMOTE, compared with SMOTE and GAN. The SMOTified-GAN and the proposed GANified-SMOTE were able to perform equally well across different amounts of generated fraud samples.https://www.mdpi.com/2227-7072/11/3/110class imbalancedata generationdeep learningfinancial fraud detection |
| spellingShingle | Patience Chew Yee Cheah Yue Yang Boon Giin Lee Enhancing Financial Fraud Detection through Addressing Class Imbalance Using Hybrid SMOTE-GAN Techniques International Journal of Financial Studies class imbalance data generation deep learning financial fraud detection |
| title | Enhancing Financial Fraud Detection through Addressing Class Imbalance Using Hybrid SMOTE-GAN Techniques |
| title_full | Enhancing Financial Fraud Detection through Addressing Class Imbalance Using Hybrid SMOTE-GAN Techniques |
| title_fullStr | Enhancing Financial Fraud Detection through Addressing Class Imbalance Using Hybrid SMOTE-GAN Techniques |
| title_full_unstemmed | Enhancing Financial Fraud Detection through Addressing Class Imbalance Using Hybrid SMOTE-GAN Techniques |
| title_short | Enhancing Financial Fraud Detection through Addressing Class Imbalance Using Hybrid SMOTE-GAN Techniques |
| title_sort | enhancing financial fraud detection through addressing class imbalance using hybrid smote gan techniques |
| topic | class imbalance data generation deep learning financial fraud detection |
| url | https://www.mdpi.com/2227-7072/11/3/110 |
| work_keys_str_mv | AT patiencechewyeecheah enhancingfinancialfrauddetectionthroughaddressingclassimbalanceusinghybridsmotegantechniques AT yueyang enhancingfinancialfrauddetectionthroughaddressingclassimbalanceusinghybridsmotegantechniques AT boongiinlee enhancingfinancialfrauddetectionthroughaddressingclassimbalanceusinghybridsmotegantechniques |