14th IIAI International Congress on Advanced Applied Informatics, pp. 361-368, July 9, 2023
13th International Conference on Smart Computing and Artificial Intelligence (SCAI 2023) in 14th IIAI International Congress on Advanced Applied Informatics (IIAI AAI 2023)
This study proposes a new generative adversarial network (GAN) for generating realistic orders in financial markets. In some previous works, GANs for financial markets generated fake orders in continuous spaces because of GAN architectures' learning limitations. However, in reality, the orders are discrete. For example, the orders have minimum order price unit, or order types. Thus, we change the generation method to place the generated fake orders into discrete spaces in this study. Because this change disabled the ordinary GAN learning algorithm, this study employed a policy gradient, frequently used in reinforcement learning, for the learning algorithm. In our experiments, we processed significant volumes of order data over half a year and evaluated our model. Through our experiments, we show that our proposed model outperforms previous models in generated order distribution. As an additional benefit of introducing the policy gradient, the entropy of the generated policy can be used to check GAN's learning status. In the future, higher performance GANs, better evaluation methods, or the applications of our GANs can be addressed.
Generative adversarial networks (GAN); Financial markets; Policy gradient; Order generation;
arXiv:2204.13338 (doi.org/10.48550/arXiv.2204.13338), ssrn.com/abstract=4454626 (doi.org/10.2139/ssrn.4454626)
10.1109/IIAI-AAI59060.2023.00077
@inproceedings{Hirano2023-iiaiaai-pgsgan,
title={{Policy Gradient Stock GAN for Realistic Discrete Order Data Generation in Financial Markets}},
author={Masanori HIRANO and Hiroki SAKAJI and Kiyoshi IZUMI},
booktitle={14th IIAI International Congress on Advanced Applied Informatics},
isbn={979-8-3503-2422-8},
pages={361-368},
publisher={IEEE},
doi={10.1109/IIAI-AAI59060.2023.00077},
archivePrefix={arXiv},
arxivId={2204.13338},
year={2023}
}