Page 486 - ISC PROCEEDINGS 21.4

downstream utility. The study further contributes actionable policy recommendations
categorized for regulators, financial institutions, and researchers. These
recommendations offer a roadmap for integrating Financial GANs into supervisory
sandboxes and production pipelines while ensuring measurable privacy and reliability.
Ultimately, this research highlights how governing synthetic data as a digital asset can
safely accelerate the economic transformation of the financial sector.

References
[1]. Allen, D. E., Mushunje, L., & Peiris, S. (2024). GANs and synthetic financial data:
calculating VaR*. Applied Economics, 1–16.
https://doi.org/10.1080/00036846.2024.2365456
[2]. Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014). Empirical evaluation of
gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555.
[3]. Efimov, D., Xu, D., Kong, L., Nefedov, A., & Anandakrishnan, A. (2020). Using
generative adversarial networks to synthesize artificial financial datasets. arXiv: Learning.
https://arxiv.org/pdf/2002.02271v1.pdf
[4]. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural
computation, 9(8), 1735-1780.
[5]. Jin, Z. C., Fu, R., Zhuang, Y., & Sudjianto, A. (2024). Default Risk Model Using
Conditional Generative Adversarial Net by High-Dimensional Financial Time-Series
Generation. The Journal of Financial Data Science, jfds.2024.1.162.
https://doi.org/10.3905/jfds.2024.1.162
[6]. Labiad, B., Berrado, A., & Benabbou, L. (2024). Generative Adversarial Neural
Networks for Realistic Stock Market Simulations. International Journal of Advanced
Computer Science & Applications, 15(3).
[7]. Lea, C., Vidal, R., Reiter, A., & Hager, G. D. (2016, October). Temporal
convolutional networks: A unified approach to action segmentation. In European
conference on computer vision (pp. 47-54). Cham: Springer International Publishing.
[8]. Li, X., Metsis, V., Wang, H., & Ngu, A. H. H. (2022, June). Tts-gan: A transformer-
based time-series generative adversarial network. In International conference on artificial
intelligence in medicine (pp. 133-143). Cham: Springer International Publishing.
[9]. Mehri, H., Hawkin, J., Nickerson, K. L., Bihlo, A., & Shoeleh, F. (2024). BankGAN:
A Generative Model for Synthetic Financial Transactions. In Canadian AI.
[10]. Radford, A., Metz, L., & Chintala, S. (2016). Unsupervised representation
learning with deep convolutional generative adversarial networks. In Proceedings of the
4th International Conference on Learning Representations (ICLR 2016), San Juan, Puerto
Rico, May 2016. ICLR.
[11]. Ramachandra, P., & Vaithiyanathan, S. (2025). Fed-DPSDG-WGAN:
Differentially Private Synthetic Data Generation for Loan Default Prediction via Federated
Wasserstein GAN. IEEE Access, 13, 52069–52084.
https://doi.org/10.1109/ACCESS.2025.3552487
[12]. Takahashi, S., Chen, Y., & Tanaka-Ishii, K. (2019). Modeling financial time-series
with generative adversarial networks. Physica A: Statistical Mechanics and its Applications,
527, Art. no. 121261. https://doi.org/10.1016/j.physa.2019.121261
[13].Wiese, M., Knobloch, R., Korn, R., & Kretschmer, P. (2020). Quant GANs: Deep
generation of financial time series. Quantitative Finance, 20(9), 1419–1440.
https://doi.org/10.1080/14697688.2020.1730426

485