Generative Adversarial Synthesis of High-Fidelity Payment Transaction Streams
Keywords:
synthetic data, generative adversarial networks, transaction modeling, privacy preservation, regulatory complianceAbstract
Testing and validating is essential for high-fidelity synthetic transaction streams in financial systems without compromising sensitive data. The objective of this paper is to present a generative adversarial network (GAN)-based framework which is suited for the synthesis of large-scale payment authorization datasets. The proposed architecture deals with both temporal dynamics and monetary distributions, at the same time incorporating domain-specific constraints to preserve regulatory compliance and ensure transaction plausibility.
Downloads
References
I. Goodfellow et al., “Generative adversarial nets,” Advances in Neural Information Processing Systems, vol. 27, pp. 2672–2680, 2014.
L. Esteban, S. L. Hyland, and G. Rätsch, “Real-valued (medical) time series generation with recurrent conditional GANs,” arXiv preprint arXiv:1706.02633, 2017.
X. Li, G. Li, and Y. Lin, “Financial data synthesis via generative adversarial networks,” Proceedings of the 2019 IEEE International Conference on Big Data (Big Data), pp. 1966–1975, 2019.
A. Choi, S. Biswal, B. Malin, J. Duke, W. F. Stewart, and J. Sun, “Generating multi-label discrete patient records using generative adversarial networks,” Machine Learning for Healthcare Conference, pp. 286–305, 2017.
T. Xu, P. Zhang, Q. Huang, H. Zhang, Z. Gan, X. Huang, and X. He, “StackGAN: Text to photo-realistic image synthesis with stacked generative adversarial networks,” IEEE International Conference on Computer Vision (ICCV), pp. 5907–5915, 2017.
A. Yoon, J. Jordon, and M. van der Schaar, “GANs for medical image synthesis,” arXiv preprint arXiv:1809.04217, 2018.
M. Mirza and S. Osindero, “Conditional generative adversarial nets,” arXiv preprint arXiv:1411.1784, 2014.
C. Bowles, E. R. Chen, G. Guerrero, J. Bentley, R. L. Gunn, C. P. Hammers, A. W. Rueckert, and D. C. Alexander, “GAN augmentation: Augmenting training data using generative adversarial networks,” arXiv preprint arXiv:1810.10863, 2018.
S. Jordon, J. Yoon, and M. van der Schaar, “PATE-GAN: Generating synthetic data with differential privacy guarantees,” International Conference on Learning Representations (ICLR), 2019.
C. Xu, D. Jiang, Y. Fang, M. Zhan, W. Yuan, and W. Ren, “A comprehensive survey on privacy-preserving federated learning: A taxonomy, review, and future directions,” IEEE Transactions on Neural Networks and Learning Systems, 2020.
Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015.
J. Lin, S. Keogh, L. Wei, and S. Lonardi, “Experiencing SAX: A novel symbolic representation of time series,” Data Mining and Knowledge Discovery, vol. 15, no. 2, pp. 107–144, 2007.
M. Arjovsky, S. Chintala, and L. Bottou, “Wasserstein GAN,” International Conference on Machine Learning, pp. 214–223, 2017.
A. Veeramachaneni, K. Chilimbi, and J. Ko, “Towards generating synthetic data for financial services,” NIPS Workshop on Machine Learning for Finance, 2018.
A. Beutel, J. Chen, Z. Zhao, and E. H. Chi, “Data decisions and theoretical implications when adversarially learning fair representations,” Conference on Fairness, Accountability, and Transparency, pp. 16–26, 2017.
M. Abadi, A. Chu, I. Goodfellow, H. B. McMahan, I. Mironov, K. Talwar, and L. Zhang, “Deep learning with differential privacy,” Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, pp. 308–318, 2016.
G. Louppe, L. Wehenkel, A. Sutera, and P. Geurts, “Learning to detect adversarial examples with generative models,” arXiv preprint arXiv:1703.00410, 2017.
A. Creswell, T. White, V. Dumoulin, K. Arulkumaran, B. Sengupta, and A. A. Bharath, “Generative adversarial networks: An overview,” IEEE Signal Processing Magazine, vol. 35, no. 1, pp. 53–65, 2018.
J. Yoon, J. Jordon, and M. van der Schaar, “Time-series generative adversarial networks,” Advances in Neural Information Processing Systems, pp. 5508–5518, 2019.
R. Salakhutdinov and G. E. Hinton, “Deep Boltzmann machines,” Artificial Intelligence and Statistics, pp. 448–455, 2009.
