STBM+: Advanced Stochastic Trading Behavior Model for Financial Markets based on Residual Blocks or Transformers

Masanori HIRANO, Kiyoshi IZUMI, Hiroki SAKAJI

The 35th Annual Conference of the Japanese Society for Artificial Intelligence, p. 2N1-IS-2a-03, June 9, 2021

Conference

The 35th Annual Conference of the Japanese Society for Artificial Intelligence (JSAI2021)

Abstract

This paper proposes a new model to reverse engineer and predict traders' behaviors for financial market. In this model, we used an architecture based on the transformer and residual block, and a loss function based on Kullback-Leibler divergence. In addition, we established a new evaluation metric, and consequently, succeeded in constructing a model that outperforms conventional methods and has an efficient architecture. In the future, we will build a model with higher performance and versatility. Moreover, we will introduce this model to financial simulations.

Keywords

Financial Market; Machine learning; Trader behavior;

doi

10.11517/pjsai.JSAI2021.0_2N1IS2a03

bibtex

@inproceedings{Hirano2021-jsai35,
  title={{STBM+: Advanced Stochastic Trading Behavior Model for Financial Markets based on Residual Blocks or Transformers}},
  author={Masanori HIRANO and Kiyoshi IZUMI and Hiroki SAKAJI},
  booktitle={The 35th Annual Conference of the Japanese Society for Artificial Intelligence},
  pages={2N1-IS-2a-03},
  doi={10.11517/pjsai.JSAI2021.0_2N1IS2a03},
  year={2021}
}