Using generative adversarial networks to synthesize artificial financial datasets
This work addresses the need for synthetic financial data for researchers and practitioners, but it is incremental as it applies an existing method (GANs) to a new domain.
The paper tackles the problem of generating realistic financial data for research and benchmarking by using Generative Adversarial Networks (GANs), showing that properly trained GANs can replicate American Express datasets with high fidelity.
Generative Adversarial Networks (GANs) became very popular for generation of realistically looking images. In this paper, we propose to use GANs to synthesize artificial financial data for research and benchmarking purposes. We test this approach on three American Express datasets, and show that properly trained GANs can replicate these datasets with high fidelity. For our experiments, we define a novel type of GAN, and suggest methods for data preprocessing that allow good training and testing performance of GANs. We also discuss methods for evaluating the quality of generated data, and their comparison with the original real data.