Comparative Analysis of Machine Learning Algorithms using GANs through Credit Card Fraud Detection
Authors: Strelcenia, E. and Prakoonwit, S.
Journal: Proceedings - 2022 International Conference on Computing, Networking, Telecommunications and Engineering Sciences Applications, CoNTESA 2022
Pages: 1-5
DOI: 10.1109/CoNTESA57046.2022.10011268
Abstract:In more recent years, credit card fraudulent transactions became a major problem. These fraudulent transactions not only incur huge monetary losses to commercial banks and financial institutions, but also stress and trouble to the lives of customers. Furthermore, with the passage of time this issue is increasing and the monetary loss is expected to increase significantly. However, efficient fraud detecting and prevention measures can trim down the monetary loss due to financial fraud activities. Credit card fraud detection has gained much interest from academia. Generative Adversarial Networks (GANs) are an effective class of generative approaches that has been able to generate synthetic data to assist with the classification of credit card fraudulent activities. In this research study we're going to compare architectures of various GAN models which demonstrate the evolution of these models. It was observed that GANs have received much attention from researchers and also attained promising results in the field of credit card fraud detection.
https://eprints.bournemouth.ac.uk/38331/
Source: Scopus
Comparative Analysis of Machine Learning Algorithms using GANs through Credit Card Fraud Detection
Authors: Strelcenia, E. and Prakoonwit, S.
Conference: 2022 International Conference on Computing, Networking, Telecommunications & Engineering Sciences Applications (CoNTESA)
Dates: 15-16 December 2022
Journal: Proceedings - 2022 International Conference on Computing, Networking, Telecommunications and Engineering Sciences Applications, CoNTESA 2022
Pages: 1-5
Place of Publication: IEEE Xplore
ISBN: 9798350398014
DOI: 10.1109/CoNTESA57046.2022.10011268
Abstract:In more recent years, credit card fraudulent transactions became a major problem. These fraudulent transactions not only incur huge monetary losses to commercial banks and financial institutions, but also stress and trouble to the lives of customers. Furthermore, with the passage of time this issue is increasing and the monetary loss is expected to increase significantly. However, efficient fraud detecting and prevention measures can trim down the monetary loss due to financial fraud activities. Credit card fraud detection has gained much interest from academia. Generative Adversarial Networks (GANs) are an effective class of generative approaches that has been able to generate synthetic data to assist with the classification of credit card fraudulent activities. In this research study we're going to compare architectures of various GAN models which demonstrate the evolution of these models. It was observed that GANs have received much attention from researchers and also attained promising results in the field of credit card fraud detection.
https://eprints.bournemouth.ac.uk/38331/
Source: Manual
Preferred by: Emilija Strelcenia
Comparative Analysis of Machine Learning Algorithms using GANs through Credit Card Fraud Detection
Authors: Strelcenia, E. and Prakoonwit, S.
Conference: 2022 International Conference on Computing, Networking, Telecommunications & Engineering Sciences Applications (CoNTESA)
Pages: 1-5
Publisher: IEEE
ISBN: 9798350398014
Abstract:In more recent years, credit card fraudulent transactions became a major problem. These fraudulent transactions not only incur huge monetary losses to commercial banks and financial institutions, but also stress and trouble to the lives of customers. Furthermore, with the passage of time this issue is increasing and the monetary loss is expected to increase significantly. However, efficient fraud detecting and prevention measures can trim down the monetary loss due to financial fraud activities. Credit card fraud detection has gained much interest from academia. Generative Adversarial Networks (GANs) are an effective class of generative approaches that has been able to generate synthetic data to assist with the classification of credit card fraudulent activities. In this research study we're going to compare architectures of various GAN models which demonstrate the evolution of these models. It was observed that GANs have received much attention from researchers and also attained promising results in the field of credit card fraud detection.
https://eprints.bournemouth.ac.uk/38331/
Source: BURO EPrints