生成式对抗网络在金融数据中的应用

崔毅浩; 刘森; 叶广楠

doi:10.11959/j.issn.2096-109x.2024047

您当前的位置：

首页 >

文章列表页 >

生成式对抗网络在金融数据中的应用

学术论文 | 更新时间：2024-08-14

- 生成式对抗网络在金融数据中的应用
- Application of generative adversarial networks for financial data
- 网络与信息安全学报 2024年10卷第3期页码：156-174
- 作者机构：
  
  复旦大学金融科技研究院，上海 200433
- 作者简介：
  
  [ "崔毅浩（1997- ），男，上海人，复旦大学硕士生，主要研究方向为金融科技、表格数据仿真。" ]
  [ "刘森（1986- ），男，湖南怀化人，复旦大学副研究员，主要研究方向为分布式系统互联和应用性能优化。" ]
  [ "叶广楠（1985- ），男，广东龙州人，复旦大学研究员、博士生导师，主要研究方向为金融科技、图模型算法、多模态特征融合、计算机视觉。" ]
- 基金信息：
  
  中国工程院战略研究与咨询项目;Strategic Research and Consulting Project of the Chinese Academy of Engineering(2023-33-14);上海市自然科学基金(23ZR1404900);国家重点研发计划项目(2023YFC3305200);云南省重大科技专项计划(202402AD080005)
- DOI：10.11959/j.issn.2096-109x.2024047
  中图分类号： TP309;F832
- 收稿：2023-02-16，
  
  修回：2024-05-26，
  
  纸质出版：2024-06-25
- 稿件说明：
移动端阅览
崔毅浩, 刘森, 叶广楠. 生成式对抗网络在金融数据中的应用[J]. 网络与信息安全学报, 2024, 10(3): 156-174.

CUI Y H, LIU S, YE G N. Application of generative adversarial networks for financial data[J]. Chinese Journal of Network and Information Security, 2024, 10(3): 156-174.
崔毅浩, 刘森, 叶广楠. 生成式对抗网络在金融数据中的应用[J]. 网络与信息安全学报, 2024, 10(3): 156-174. DOI： 10.11959/j.issn.2096-109x.2024047.

CUI Y H, LIU S, YE G N. Application of generative adversarial networks for financial data[J]. Chinese Journal of Network and Information Security, 2024, 10(3): 156-174. DOI： 10.11959/j.issn.2096-109x.2024047.

摘要

数据作为国家基础性战略资源和关键生产要素，是经济社会发展的基础资源和创新引擎。金融行业作为数据的密集型和科技驱动型行业，实现数据资产的优化配置，是促进产业升级的关键因素。但金融数据普遍存在数据分布不均衡、数据信息不对称以及“数据孤岛”等问题，导致数据无法充分发挥其价值。为了克服这些挑战，金融机构积极采用各种生成模型合成高度逼真的数据，以打破数据壁垒和垄断，成为未来金融业发展的趋势和方向。生成式对抗网络（generative adversarial network，GAN）是最流行的模型之一，在各个领域都有不俗的表现。其在金融表格数据生成、金融时间序列生成以及金融欺诈检测等方面也展现出广泛的应用潜力。文章介绍了GAN模型相较其他生成模型在金融领域的优势；对自2014年生成式对抗网络被提出以来的可被应用于金融领域的GAN模型进行整理，并对各模型的原理进行介绍；探讨GAN模型在生成金融表格数据、生成金融时间序列、金融欺诈检测等金融数据领域中的应用实践；最后结合中国的实际情况，分析了GAN在未来面临的挑战及发展方向。

Abstract

Data

recognized as a fundamental strategic resource and key production factor for a nation

has served as the foundational resource and innovation engine for economic and social development. The financial industry

characterized by its data-intensive and technology-driven nature

necessitates the optimal allocation of data assets to facilitate industrial upgrading. However

financial data commonly exhibits issues such as uneven distribution

information asymmetry

and data silos

which have prevented data from fully realizing its value. To address these challenges

various generative models have been actively adopted by financial institutions to synthesize highly realistic data

thereby breaking down data barriers and monopolies

and shaping the future trend of the financial industry. Among these models

Generative Adversarial Networks (GANs) have emerged as particularly popular

demonstrating impressive performance across various fields and showing great potential in generating financial tabular data

financial time series

and detecting financial fraud. The advantages of the GAN model compared with other generative models in the financial field were analyzed. The GAN models that have been applied to the financial field since Generative Adversarial Networks were proposed in 2014 were presented

and the principles of each model were introduced. The application practice of the GAN model in generating financial tabular data

generating financial time series

and financial fraud detection

as well as other financial data fields

was explored. Finally

the challenges and development direction of GANs for the future were discussed

taking into account the actual situation in China.

关键词

Keywords

references

鲁金彪 , 胡国强 , 周金赞 , 等 . 金融数据安全技术现状与趋势研究 [J ] . 中国金融电脑 , 2022 ( 5 ): 39 - 43 .

LU J B , HU G Q , ZHOU J Z , et al . Research on the present situation and trend of financial data security technology [J ] . Financial Computer of China , 2022 ( 5 ): 39 - 43 .

朱建明 , 杨鸿瑞 . 金融科技中数据安全的挑战与对策 [J ] . 网络与信息安全学报 , 2019 , 5 ( 4 ): 71 - 79 .

ZHU J M , YANG H R . Data security challenges and countermeasures in financial technology [J ] . Chinese Journal of Network and Information Security , 2019 , 5 ( 4 ): 71 - 79 .

张旭东 . 金融数据安全与个人信息保护 [J ] . 清华金融评论 , 2021 ( 12 ): 93 - 95 .

ZHANG X D . Financial data security and personal information protection [J ] . Tsinghua Financial Review , 2021 ( 12 ): 93 - 95 .

ASSEFA S A , DERVOVIC D , MAHFOUZ M , et al . Generating synthetic data in finance: opportunities, challenges and pitfalls [C ] // Proceedings of the First ACM International Conference on AI in Finance . New York : ACM , 2020 : 1 - 8 .

FAN J , LIU T Y , LI G L , et al . Relational data synthesis using generative adversarial networks: a design space exploration [EB ] . arXiv Preprint arXiv: 2008.12763 , 2020 .

TAKAHASHI S , CHEN Y , TANAKA-ISHII K . Modeling financial time-series with generative adversarial networks [J ] . Physica A: Statistical Mechanics and Its Applications , 2019 , 527 : 121261 .

CONT R . Empirical properties of asset returns: stylized facts and statistical issues [J ] . Quantitative Finance , 2001 , 1 ( 2 ): 223 - 236 .

BAUWENS L , LAURENT S , ROMBOUTS J V K . Multivariate GARCH models: a survey [J ] . Journal of Applied Econometrics , 2006 , 21 ( 1 ): 79 - 109 .

BANKES S C . Agent-based modeling: a revolution? [J ] . Proceedings of the National Academy of Sciences of the United States of America , 2002 , 99 ( Suppl 3 ): 7199 - 7200 .

KINGMA D P , WELLING M . Auto-encoding variational bayes [EB ] . arXiv Preprint arXiv: 1312.6114 , 2013 .

HUANG H B , LI Z H , HE R , et al . IntroVAE: introspective variational autoencoders for photographic image synthesis [EB ] . arXiv Preprint arXiv: 1807.06358 , 2018 .

KINGMA D P , SALIMANS T , JOZEFOWICZ R , et al . Improved variational inference with inverse autoregressive flow [C ] // Proceedings of the 30th International Conference on Neural Information Processing Systems . New York : ACM , 2016 : 4743 - 4751 .

RAZAVI A , VAN DEN OORD A , VINYALS O . Generating diverse high-fidelity images with VQ-VAE-2 [EB ] . arXiv Preprint arXiv: 1906.00446 , 2019 .

VAN DEN OORD A , KALCHBRENNER N , KAVUKCUOGLU K . Pixel recurrent neural networks [J ] . 33rd International Conference on Machine Learning , ICML 2016, 2016 , 4 : 2611 - 2620 .

VAHDAT A , KAUTZ J . NVAE: A deep hierarchical variational autoencoder [J ] . Advances in neural information processing systems , 2020 , 33 : 19667 - 19679 .

REZENDE D , MOHAMED S . Variational inference with normalizing flows [EB ] . arXiv Preprint arXiv: 1505.05770 , 2015 .

DINH L , SOHL-DICKSTEIN J , BENGIO S . Density estimation using Real NVP [EB ] . arXiv Preprint arXiv: 1605.08803 , 2016 .

KINGMA D P , DHARIWAL P , YANG C L , et al . Glow: generative flow with invertible 1x1 convolutions [EB ] . arXiv Preprint arXiv: 1807.03039 , 2018 .

OORD A , DIELEMAN S , ZEN H , et al . Wavenet: A generative model for raw audio [EB ] . arXiv Preprint arXiv: 1609.03499 , 2016 .

YANG L , ZHANG Z L , HONG S D , et al . Diffusion models: a comprehensive survey of methods and applications [J ] . ACM Computing Surveys , 2022 , 56 : 1 - 39 .

GOODFELLOW I , POUGET-ABADIE J , MIRZA M , et al . Generative adversarial nets [J ] . Advances in neural information processing systems , 2014 , 27 .

KARRAS T , LAINE S , AITTALA M , et al . Analyzing and improving the image quality of StyleGAN [C ] // Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE Press , 2020 : 8107 - 8116 .

WANG Z W , SHE Q , WARD T E . Generative adversarial networks in computer vision: a survey and taxonomy [J ] . ACM Computing Surveys , 2021 , 54 ( 2 ): 37 .

SAFAVIAN S R , LANDGREBE D . A survey of decision tree classifier methodology [J ] . IEEE Transactions on Systems, Man, and Cybernetics , 1991 , 21 ( 3 ): 660 - 674 .

曹莹 , 苗启广 , 刘家辰 , 等 . AdaBoost算法研究进展与展望 [J ] . 自动化学报 , 2013 , 39 ( 6 ): 745 - 758 .

CAO Y , MIAO Q G , LIU J C , et al . Advance and prospects of AdaBoost algorithm [J ] . Acta Automatica Sinica , 2013 , 39 ( 6 ): 745 - 758 .

ZHU J Y , ZHANG R , PATHAK D , et al . Toward multimodal image-to-image translation [EB ] . arXiv Preprint arXiv: 1711 . 11586 v 4 , 2017 .

LIU M Y , TUZEL O . Coupled generative adversarial networks [EB ] . arXiv Preprint arXiv: 1606.07536 , 2016 .

ZHU J Y , PARK T , ISOLA P , et al . Unpaired image-to-image translation using cycle-consistent adversarial networks [C ] // Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV) . Piscataway : IEEE Press , 2017 : 2242 - 2251 .

CHEN X , DUAN Y , HOUTHOOFT R , et al . InfoGAN: interpretable representation learning by information maximizing generative adversarial nets [C ] // Proceedings of the 30th International Conference on Neural Information Processing Systems . New York : ACM , 2016 : 2180 - 2188 .

ISOLA P , ZHU J Y , ZHOU T H , et al . Image-to-image translation with conditional adversarial networks [C ] // Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE Press , 2017 : 5967 - 5976 .

LEDIG C , THEIS L , HUSZÁR F , et al . Photo-realistic single image super-resolution using a generative adversarial network [C ] // Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE Press , 2017 : 105 - 114 .

PARK N , MOHAMMADI M , GORDE K , et al . Data synthesis based on generative adversarial networks [EB ] . arXiv Preprint arXiv: 1806.03384 , 2018 .

XU L , VEERAMACHANENI K . Synthesizing tabular data using generative adversarial networks [EB ] . arXiv Preprint arXiv: 1811.11264 , 2018 .

XU L , SKOULARIDOU M , CUESTA-INFANTE A , et al . Modeling Tabular data using Conditional GAN [EB ] . arXiv Preprint arXiv: 1907.00503 , 2019 .

ESPINOSA E , FIGUEIRA A . On the quality of synthetic generated tabular data [J ] . Mathematics , 2023 , 11 ( 15 ): 3278 .

RAJABI A , GARIBAY O O . TabFairGAN: fair tabular data generation with generative adversarial networks [EB ] . arXiv Preprint arXiv: 2109.00666 , 2021 .

ZHAO Z L , KUNAR A , VAN DER SCHEER H , et al . CTAB-GAN: effective table data synthesizing [EB ] . arXiv Preprint arXiv: 2102.08369 , 2021 .

ZHAO Z L , KUNAR A , BIRKE R , et al . CTAB-GAN+: enhancing tabular data synthesis [EB ] . arXiv Preprint arXiv: 2204.00401 , 2022 .

BOJCHEVSKI A , SHCHUR O , ZÜGNER D , et al . NetGAN: generating graphs via random walks [EB ] . arXiv Preprint arXiv: 1803.00816 , 2018 .

ZHOU D W , ZHENG L C , XU J J , et al . Misc-GAN: a multi-scale generative model for graphs [J ] . Frontiers in Big Data , 2019 , 2 : 3 .

DE CAO N , KIPF T . MolGAN: an implicit generative model for small molecular graphs [EB ] . arXiv Preprint arXiv: 1805.11973 , 2018 .

YOON J , JARRETT D , VAN D SCHAAR M . Time-series generative adversarial networks [C ] // Proceedings of the 33rd International Conference on Neural Information Processing Systems . 2019 : 5508 - 5518 .

DE M P F . Enriching financial datasets with generative adversarial networks [D ] . MS thesis, Delft University of Technology , The Netherlands , 2019 .

MAGNUS W , ROBERT K , RALF K , et al . Quant GANs: deep generation of financial time series [J ] . Quantitative Finance , 2020 , 20 ( 9 ): 1419 - 1440 .

JOLICOEUR-MARTINEAU A . The relativistic discriminator: a key element missing from standard GAN [EB ] . arXiv Preprint arXiv: 1807.00734 , 2018 .

EFIMOV D , XU D , KONG L Y , et al . Using generative adversarial networks to synthesize artificial financial datasets [EB ] . arXiv Preprint arXiv: 2002.02271 , 2020 .

LIAO S J , NI H , SZPRUCH L , et al . Conditional sig-Wasserstein GANs for time series generation [EB ] . arXiv Preprint arXiv: 2006.05421 , 2020 .

MUTHUKUMAR P , ZHONG J . A stochastic time series model for predicting financial trends using nlp [EB ] . arXiv Preprint arXiv: 2102.01290 , 2021 .

GUPTA A , JOHNSON J , LI F F , et al . Social GAN: socially acceptable trajectories with generative adversarial networks [C ] // Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE Press , 2018 : 2255 - 2264 .

ZHOU X Y , PAN Z S , HU G H Y , et al . Stock market prediction on high-frequency data using generative adversarial nets [J ] . Mathematical Problems in Engineering , 2018 , 4 : 1 - 11 .

WU W J , HUANG F , KAO Y D , et al . Prediction method of multiple related time series based on generative adversarial networks [J ] . Information , 2021 , 12 ( 2 ): 55 .

MIRZA M , OSINDERO S . Conditional generative adversarial nets [EB ] . arXiv Preprint arXiv: 1411.1784 , 2014 .

ECKERLI F , OSTERRIEDER J . Generative adversarial networks in finance: an overview [EB ] . arXiv Preprint arXiv: 2106.06364 , 2021 .

MARIANI G , ZHU Y D , LI J B , et al . PAGAN: portfolio analysis with generative adversarial networks [EB ] . arXiv Preprint arXiv: 1909.10578 , 2019 .

KIM Y , KANG D , JEON M , et al . GAN-MP hybrid heuristic algorithm for non-convex portfolio optimization problem [J ] . The Engineering Economist , 2019 , 64 ( 3 ): 1 - 31 .

SUN H , DENG Z , CHEN H , et al . Decision-aware conditional GANs for time series data [C ] // Proceedings of the Fourth ACM International Conference on AI in Finance . New York : ACM , 2023 : 36 - 45 .

MARTI G . CORRGAN: sampling realistic financial correlation matrices using generative adversarial networks [C ] // Proceedings of the ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) . Piscataway : IEEE Press , 2020 : 8459 - 8463 .

LEANGARUN T , TANGAMCHIT P , THAJCHAYAPONG S . Stock price manipulation detection using generative adversarial networks [C ] // Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence (SSCI) . Piscataway : IEEE Press , 2018 : 2104 - 2111 .

SETHIA A , PATEL R , RAUT P . Data Augmentation using Generative models for Credit Card Fraud Detection [C ] // Proceedings of the 2018 4th International Conference on Computing Communication and Automation (ICCCA) . Piscataway : IEEE Press , 2018 : 1 - 6 .

ZHANG Z H , YANG L J , CHEN L G , et al . A generative adversarial network-based method for generating negative financial samples [J ] . International Journal of Distributed Sensor Networks , 2020 , 16 ( 2 ): 155014772090705 .

BOUROU S , EL SAER A , VELIVASSAKI T H , et al . A review of tabular data synthesis using GANs on an IDS dataset [J ] . Information , 2021 , 12 ( 09 ): 375 .

ARMANIOUS K , JIANG C M , FISCHER M , et al . MedGAN: medical image translation using GANs [J ] . Computerized Medical Imaging and Graphics , 2020 , 79 : 101684 .

RADFORD A , METZ L , CHINTALA S , et al . Unsupervised representation learning with deep convolutional generative adversarial networks [EB ] . arXiv Preprint arXiv: 1511.06434 , 2015 .

HOCHREITER S , SCHMIDHUBER J . Long short-term memory [J ] . Neural computation , 1997 , 9 ( 8 ): 1735 - 1780 .

ZHANG H , GOODFELLOW I , METAXAS D , et al . Self-attention generative adversarial networks [EB ] . arXiv Preprint arXiv: 1805.08318 , 2018 .

ARJOVSKY M , CHINTALA S , BOTTOU L . Wasserstein generative adversarial networks [C ] // Proceedings of the 34th International Conference on Machine Learning-Volume 70 . New York : ACM , 2017 : 214 - 223 .

GULRAJANI I , AHMED F , ARJOVSKY M , et al . Improved training of Wasserstein GANs [EB ] . arXiv Preprint arXiv: 1704.00028 , 2017 .

KINGMA D P , BA J . Adam: a method for stochastic optimization [EB ] . arXiv Preprint arXiv: 1412.6980 , 2014 .

LEA C , VIDAL R , REITER A , et al . Temporal convolutional networks: A unified approach to action segmentation [C ] // Computer Vision–ECCV 2016 Workshops: Amsterdam , The Netherlands, October 8-10 and 15 - 16 , 2016 , Proceedings, Part III 14 . Springer International Publishing, 2016: 47 - 54 .

AGGARWAL R K , WU G . Stock market manipulation-theory and evidence [C ] // AFA 2004 San Diego Meetings . 2003 .

CAO Y , LI Y H , COLEMAN S , et al . Detecting price manipulation in the financial market [C ] // Proceedings of the 2014 IEEE Conference on Computational Intelligence for Financial Engineering & Economics (CIFEr) . Piscataway : IEEE Press , 2014 : 77 - 84 .

BARKER K J , D'AMATO J , SHERIDON P . Credit card fraud: awareness and prevention [J ] . Journal of financial crime , 2008 , 15 ( 4 ): 398 - 410 .

LOVE D , AGGARWAL N , STATNIKOV A , et al . An automated system for data attribute anomaly detection [C ] // Proceedings of KDD 2017 Workshop on Anomaly Detection in Finance . PMLR : ADF , 2018 : 95 - 101 .

DANKAR F K , IBRAHIM M . FAKE it till you make it: Guidelines for effective synthetic data generation [J ] . Applied Sciences , 2021 , 11 ( 5 ): 2158 .

GĄSIORKIEWICZ L , MONKIEWICZ J , MONKIEWICZ M . Technology-driven innovations in financial services: The rise of alternative finance [J ] . Foundations of Management , 2020 , 12 ( 1 ): 137 - 150 .

MONTANTES J . Deep learning in finance: Is this the future of the financial industry [J ] . Digital Finance . 2023 , 5 : 1 - 2 .

LIEW S P , TAKAHASHI T , UENO M . PEARL: data synthesis via private embeddings and adversarial reconstruction learning [EB ] . arXiv Preprint arXiv: 2106.04590 , 2021 .

CHAE D K , KANG J S , KIM S W , et al . CFGAN: a generic collaborative filtering framework based on generative adversarial networks [C ] // Proceedings of the 27th ACM International Conference on Information and Knowledge Management . New York : ACM , 2018 : 137 - 146 .

DONAHUE J , JIA Y Q , VINYALS O , et al . DeCAF: a deep convolutional activation feature for generic visual recognition [J ] . 31st International Conference on Machine Learning , ICML 2014, 2014 , 2 : 988 - 996 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

车-路-云协同自动驾驶安全技术研究进展

基于区块链的跨数据中心匿名可监管身份认证方案

金融数据安全治理智能化技术与实践

人工智能模型数据泄露的攻击与防御研究综述

金融科技中数据安全的挑战与对策