Generative Adversarial Networks (GANs) for Synthetic Financial Transaction Data in AML Testing
Keywords:
Generative Adversarial Networks, Conditional GANs, synthetic financial data, Anti-Money Laundering, data privacyAbstract
It is hard to test and certify AML systems since they have to secure customer data and deal with complicated financial transaction networks. We employ conditional GANs to generate synthetic financial transaction datasets that look like genuine banking data but keep people's privacy protected. The proposed cGAN system is contextually coherent since it uses account type, transaction channel, and location identifiers. Retraining fraud detection algorithms on synthetic datasets guarantees downstream applicability, whereas K–S and Wasserstein distance assess distributional similarity and statistical integrity. Experiments demonstrate that data exhibits almost comparable behavioral distributions while maintaining privacy and adhering to regulatory standards. Datasets help researchers safely test AML scenarios in regulatory sandboxes. Synthetic data created using cGAN might help with AML testing and keeping an eye on questionable activities, all while keeping privacy and scalability in mind.
Downloads
References
R. I. T. Jensen et al., "A synthetic data set to benchmark anti-money laundering methods," Scientific Data, vol. 10, no. 661, 2023.
E. Altman et al., "Realistic synthetic financial transactions for anti-money laundering models," NeurIPS 2023 Poster, 2023.
J. Blanuša et al., "Conditional GAN-based synthetic financial modeling for street vendors in India's informal economy," Springer Journal of Financial Technology, vol. 1, no. 145, 2025.
A. Iosifidis et al., "Synthetic data generation for fraud detection using GANs," arXiv preprint arXiv:2109.12546, 2021.
R. Jaiswal and B. Singh, "Financial fraud prevention with synthetic data generation using GAN," Arya Bhatta Journal of Mathematics and Informatics, vol. 14, pp. 161–166, 2023.
R. I. T. Jensen et al., "SynthAML: A synthetic data set to benchmark anti-money laundering methods," Scientific Data, vol. 10, no. 661, 2023.
J. Blanuša et al., "Conditional GAN-based synthetic financial modeling for street vendors in India's informal economy," Springer Journal of Financial Technology, vol. 1, no. 145, 2025.
S. Z. Aftabi et al., "Fraud detection in financial statements using data mining and GAN models," Expert Systems with Applications, vol. 227, p. 120144, 2023.
C. R. Alexandre and J. Balsa, "Incorporating machine learning and a risk-based strategy in an anti-money laundering multiagent system," Expert Systems with Applications, vol. 217, p. 119500, 2023.
M. N. Ashtiani and B. Raahemi, "Intelligent fraud detection in financial statements using machine learning and data mining: A systematic literature review," IEEE Access, vol. 10, pp. 72504–72525, 2021.
R. I. T. Jensen et al., "SynthAML: A synthetic data set to benchmark anti-money laundering methods," Scientific Data, vol. 10, no. 661, 2023.
A. Iosifidis et al., "Synthetic data generation for fraud detection using GANs," arXiv preprint arXiv:2109.12546, 2021.
J. Blanuša et al., "Conditional GAN-based synthetic financial modeling for street vendors in India's informal economy," Springer Journal of Financial Technology, vol. 1, no. 145, 2025.
S. Z. Aftabi et al., "Fraud detection in financial statements using data mining and GAN models," Expert Systems with Applications, vol. 227, p. 120144, 2023.
C. R. Alexandre and J. Balsa, "Incorporating machine learning and a risk-based strategy in an anti-money laundering multiagent system," Expert Systems with Applications, vol. 217, p. 119500, 2023.
M. N. Ashtiani and B. Raahemi, "Intelligent fraud detection in financial statements using machine learning and data mining: A systematic literature review," IEEE Access, vol. 10, pp. 72504–72525, 2021.
R. I. T. Jensen et al., "SynthAML: A synthetic data set to benchmark anti-money laundering methods," Scientific Data, vol. 10, no. 661, 2023.
A. Iosifidis et al., "Synthetic data generation for fraud detection using GANs," arXiv preprint arXiv:2109.12546, 2021.
J. Blanuša et al., "Conditional GAN-based synthetic financial modeling for street vendors in India's informal economy," Springer Journal of Financial Technology, vol. 1, no. 145, 2025.
S. Z. Aftabi et al., "Fraud detection in financial statements using data mining and GAN models," Expert Systems with Applications, vol. 227, p. 120144, 2023.
