Synthesizing Individual Consumers′ Credit Historical Data Using Generative Adversarial Networks
The financial sector accumulates a massive amount of consumer data that contain the most sensitive information daily. These data are strictly limited outside the financial institutions, sometimes even within the same organization, for various reasons such as privacy laws or asset management policy....
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/3/1126 |
| _version_ | 1797407323177615360 |
|---|---|
| author | Nari Park Yeong Hyeon Gu Seong Joon Yoo |
| author_facet | Nari Park Yeong Hyeon Gu Seong Joon Yoo |
| author_sort | Nari Park |
| collection | DOAJ |
| description | The financial sector accumulates a massive amount of consumer data that contain the most sensitive information daily. These data are strictly limited outside the financial institutions, sometimes even within the same organization, for various reasons such as privacy laws or asset management policy. Financial data has never been more valuable, especially when assessed jointly with data from different industries, including healthcare, insurance, credit bureau, and research institutions. Therefore, it is critical to generate synthetic datasets that retain the statistical or latent properties of the real datasets as well as the privacy protection guaranteed. In this paper, we apply Generative Adversarial Nets (GANs) to generating synthetic consumer credit data to be used for various educational purposes, specifically in developing machine learning models. GAN is preferable to other pseudonymization methods such as masking, swapping, shuffling, or perturbation, for it does not suffer from adding more attributes or data. This study is significant because it is the first attempt to generate the synthetic data of real-world credit data in practical use. The results find that synthetic consumer credit data using GAN shows a substantial utility without severely compromising privacy and would be a useful resource for big data training programs. |
| first_indexed | 2024-03-09T03:40:40Z |
| format | Article |
| id | doaj.art-abc1cd0c45904fdca1a64a2f20657e7e |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T03:40:40Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-abc1cd0c45904fdca1a64a2f20657e7e2023-12-03T14:42:19ZengMDPI AGApplied Sciences2076-34172021-01-01113112610.3390/app11031126Synthesizing Individual Consumers′ Credit Historical Data Using Generative Adversarial NetworksNari Park0Yeong Hyeon Gu1Seong Joon Yoo2Department of Computer Science, Sejong University, Seoul 05006, KoreaDepartment of Computer Science, Sejong University, Seoul 05006, KoreaDepartment of Computer Science, Sejong University, Seoul 05006, KoreaThe financial sector accumulates a massive amount of consumer data that contain the most sensitive information daily. These data are strictly limited outside the financial institutions, sometimes even within the same organization, for various reasons such as privacy laws or asset management policy. Financial data has never been more valuable, especially when assessed jointly with data from different industries, including healthcare, insurance, credit bureau, and research institutions. Therefore, it is critical to generate synthetic datasets that retain the statistical or latent properties of the real datasets as well as the privacy protection guaranteed. In this paper, we apply Generative Adversarial Nets (GANs) to generating synthetic consumer credit data to be used for various educational purposes, specifically in developing machine learning models. GAN is preferable to other pseudonymization methods such as masking, swapping, shuffling, or perturbation, for it does not suffer from adding more attributes or data. This study is significant because it is the first attempt to generate the synthetic data of real-world credit data in practical use. The results find that synthetic consumer credit data using GAN shows a substantial utility without severely compromising privacy and would be a useful resource for big data training programs.https://www.mdpi.com/2076-3417/11/3/1126consumer credit historical datasynthetic data generationgenerative adversarial networksartificial intelligence data miningfinancial big data |
| spellingShingle | Nari Park Yeong Hyeon Gu Seong Joon Yoo Synthesizing Individual Consumers′ Credit Historical Data Using Generative Adversarial Networks Applied Sciences consumer credit historical data synthetic data generation generative adversarial networks artificial intelligence data mining financial big data |
| title | Synthesizing Individual Consumers′ Credit Historical Data Using Generative Adversarial Networks |
| title_full | Synthesizing Individual Consumers′ Credit Historical Data Using Generative Adversarial Networks |
| title_fullStr | Synthesizing Individual Consumers′ Credit Historical Data Using Generative Adversarial Networks |
| title_full_unstemmed | Synthesizing Individual Consumers′ Credit Historical Data Using Generative Adversarial Networks |
| title_short | Synthesizing Individual Consumers′ Credit Historical Data Using Generative Adversarial Networks |
| title_sort | synthesizing individual consumers credit historical data using generative adversarial networks |
| topic | consumer credit historical data synthetic data generation generative adversarial networks artificial intelligence data mining financial big data |
| url | https://www.mdpi.com/2076-3417/11/3/1126 |
| work_keys_str_mv | AT naripark synthesizingindividualconsumerscredithistoricaldatausinggenerativeadversarialnetworks AT yeonghyeongu synthesizingindividualconsumerscredithistoricaldatausinggenerativeadversarialnetworks AT seongjoonyoo synthesizingindividualconsumerscredithistoricaldatausinggenerativeadversarialnetworks |