The 23rd International Conference on Principles and Practice of Multi-Agent Systems, pp. 3-18, Nov. 19, 2020
The 23rd International Conference on Principles and Practice of Multi-Agent Systems (PRIMA 2020)
In this paper, we propose a new scheme for implementing the machine-learned trader-agent model in financial market simulations based on real data. The implementation is only focused on the high-frequency-trader market-making (HFT-MM) strategy. We first extract order data of HFT-MM traders from the real order data by clustering. Then, using the data, we build a deep learning model. Using the model, we build an HFT-MM trader model for simulations. In the simulations, we compared our new model and a traditional HFT-MM trader model in terms of divergence of the ordering behaviors. Our new trader model outperforms the traditional model. Moreover, we also found an obstacle of combination of data and simulation.
Artificial financial market; Multi-agent simulation; Machine learning; Deep learning; Data mining; High-frequency trade; Market-making; Clustering;
@inproceedings{Hirano2020-prima-financial,
title={{Implementation of Real Data for Financial Market Simulation using Clustering, Deep Learning, and Artificial Financial Market}},
author={Masanori HIRANO and Hiroyasu MATSUSHIMA and Kiyoshi IZUMI and Hiroki SAKAJI},
booktitle={The 23rd International Conference on Principles and Practice of Multi-Agent Systems},
isbn={978-3-030-69322-0},
pages={3-18},
publisher={Springer},
doi={10.1007/978-3-030-69322-0_1},
year={2020}
}