< back

STBM: Stochastic Trading Behavior Model for Financial Markets

Masanori HIRANO, Hiroyasu MATSUSHIMA, Kiyoshi IZUMI, Hiroki SAKAJI

Selected Papers from the Annual Conference of Japanese Society of Artificial Intelligence (JSAI 2020), Advances in Artificial Intelligence, vol.1357, 2021


Conference

Selected Papers from the Annual Conference of Japanese Society of Artificial Intelligence (JSAI 2020), Advances in Artificial Intelligence

Abstract

This is an extension from a selected paper from JSAI2020. In this study, we propose a stochastic model for predicting the behavior of financial market traders. First, using real ordering data that includes traders’ information, we cluster the traders and select a recognizable cluster that appears to employ a high-frequency traders’ market-making (HFT-MM) strategy. Then, we use an LSTM-based stochastic prediction model to predict the traders’ behavior. This model takes the market order book state and a trader’s ordering state as input and probabilistically predicts the trader’s actions over the next one minute. The results show that our model can outperform both a model that randomly takes actions and a conventional deterministic model. Herein, we only analyze limited trader type but, if our model is implemented to all trader types, this will increase the accuracy of predictions for the entire market.

Keywords

Machine learning; Deep learning; Data mining; High-frequency trade; Market-making; Clustering;

doi

10.1007/978-3-030-73113-7_14


bibtex

@inproceedings{Hirano2021-jsai-post,
  title={{STBM: Stochastic Trading Behavior Model for Financial Markets}},
  autor={Masanori HIRANO and Hiroyasu MATSUSHIMA and Kiyoshi IZUMI and Hiroki SAKAJI},
  booktitle={Selected Papers from the Annual Conference of Japanese Society of Artificial Intelligence (JSAI 2020), Advances in Artificial Intelligence},
  isbn={978-3-030-73113-7},
  volume={1357},
  pages={157-165},
  publisher={Springer},
  doi={10.1007/978-3-030-73113-7_14},
  year={2021}
}