Skip to main content
SpringerLink
Log in

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

  • Published:
New Generation Computing Aims and scope Submit manuscript

Abstract

This study proposes a new model to reverse engineer and predict traders’ behavior for the financial market. This trial is essential to build a more reliable simulation because the reliability of models is a fundamental issue in the increasing use of simulations. Thus, we tried to build a behavior model of financial traders through the traders’ future action predicting using the actual order data. This study focused on one category of traders employing high-frequency market-making (HFT-MM) trading in financial markets. In our experiments, we build models for predicting the next actions of each trader and evaluate how correctly these models successfully predict trades’ future actions in the next one minutes. Although the task is the same as previous work, this study newly used an architecture based on the transformer and residual block, and a loss function based on the Kullback-Leibler divergence (KLD). In addition, we established a new evaluation metric. Consequently, our new models, both transformer-based and residual-block-based models, outperformed the previous model based on LSTM in terms of both old and new evaluation metrics. These results suggested that transformer and residual block are effective in capturing traders’ behaviors. In addition, the KLD-based new loss function also showed better results than the previous MSE-based loss function. We assumed it is because the KLD-based loss function has a better fitting to this task due to its mathematical form.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Notes

  1. In fact, the JSD is not used for GAN learning; usually, cross-entropy is used. Note that the JSD is used not for the loss function but for theoretical discussion.

  2. This is our fictional name. In NLP, BERT often refers to a language model. However, ironically, there is no connotation of a language model in its abbreviation.

References

  1. Arjovsky, M., Bottou, L.: Towards principled methods for training generative adversarial networks. In: 5th international conference on learning representations (2019). arXiv:1701.04862

  2. Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein GAN (2017). arXiv:1701.07875

  3. Avellaneda, M., Stoikov, S.: High-frequency trading in a limit order book. Quant. Finance 8(3), 217–224 (2008). https://doi.org/10.1080/14697680701381228

    Article  MathSciNet  MATH  Google Scholar 

  4. Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer Normalization (2016). arXiv:1607.06450

  5. Battiston, S., Farmer, J.D., Flache, A., Garlaschelli, D., Haldane, A.G., Heesterbeek, H., Hommes, C., Jaeger, C., May, R., Scheffer, M.: Complexity theory and financial regulation: economic policy needs interdisciplinary network analysis and behavioral modeling. Science 351(6275), 818–819 (2016). https://doi.org/10.1126/science.aad0299

    Article  Google Scholar 

  6. Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of Deep Bidirectional Transformers for Language Understanding (2018). arXiv:1810.04805

  7. Dixon, M.F., Polson, N.G., Sokolov, V.O.: Deep learning for spatio-temporal modeling: Dynamic traffic flows and high frequency trading. Quant. Finance 19(4), 549–570 (2019). https://doi.org/10.1002/asmb.2399

    Article  MathSciNet  Google Scholar 

  8. Edmonds, S.M., Bruce: towards good social science. J. Artif. Soc. Soc. Simul. 8(4) (2005). https://jasss.soc.surrey.ac.uk/8/4/13.html

  9. Farmer, J.D., Foley, D.: The economy needs agent-based modelling. Nature 460(7256), 685–686 (2009). https://doi.org/10.1038/460685a

    Article  Google Scholar 

  10. Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. In: advances in neural information processing systems, 3, 2672–2680 (2014). https://proceedings.neurips.cc/paper/2014/hash/5ca3e9b122f61f8f06494c97b1afccf3-Abstract.html

  11. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: proceedings of the IEEE computer society conference on computer vision and pattern recognition, pp. 770–778. IEEE computer society (2016). https://openaccess.thecvf.com/content_cvpr_2016/html/He_Deep_Residual_Learning_ CVPR_2016_paper.html

  12. Hirano, M., Izumi, K., Matsushima, H., Sakaji, H.: Comparing actual and simulated HFT traders’ behavior for agent design. J. Artif. Soc. Soc. Simul. 23(3) (2020). https://doi.org/10.18564/jasss.4304

  13. Hirano, M., Matsushima, H., Izumi, K., Sakaji, H.: STBM: stochastic trading behavior model for financial markets. In: Yada, K., et al. (eds.) Advances in Artificial Intelligence. JSAI 2020. Advances in Intelligent Systems and Computing, vol. 1357. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-73113-7_14

    Chapter  Google Scholar 

  14. Hochreiter, S., Schmidhuber, J.: Long Short-Term Memory. Neural Comput. 9(8), 1735–1780 (1997). https://doi.org/10.1162/neco.1997.9.8.1735

    Article  Google Scholar 

  15. Kercheval, A.N., Zhang, Y.: Modelling high-frequency limit order book dynamics with support vector machines. Quant. Finance 15(8), 1315–1329 (2015). https://doi.org/10.1080/14697688.2015.1032546

    Article  MathSciNet  MATH  Google Scholar 

  16. Kim, K.: Financial time series forecasting using support vector machines. Neurocomputing 55, 307–319 (2003). https://doi.org/10.1016/S0925-2312(03)00372-2

    Article  Google Scholar 

  17. Kullback, S., Leibler, R.A.: On information and sufficiency. Ann. Mathe. Stat. 22(1), 79–86 (1951). https://www.jstor.org/stable/2236703

  18. Lux, T., Marchesi, M.: Scaling and criticality in a stochastic multi-agent model of a financial market. Nature 397(6719), 498–500 (1999). https://doi.org/10.1038/17290

    Article  Google Scholar 

  19. Mizuta, T.: An agent-based model for designing a financial market that works well (2019). arXiv:1906.06000

  20. Mizuta, T., Kosugi, S., Kusumoto, T., Matsumoto, W., Izumi, K., Yagi, I., Yoshimura, S.: Effects of Price Regulations and Dark Pools on Financial Market Stability: An Investigation by Multiagent Simulations. Intel. Syst. Acc. Finance Manag. 23(1–2), 97–120 (2016). https://doi.org/10.1002/isaf.1374

    Article  Google Scholar 

  21. Nagumo, S., Shimada, T., Yoshioka, N., Ito, N.: The effect of tick size on trading volume share in two competing stock markets. J. Phys. Soc. Japn. 86(1), 12 (2017). https://doi.org/10.7566/JPSJ.86.014801

    Article  Google Scholar 

  22. Nanex: nanex - market crop circle of the day (2010). http://www.nanex.net/FlashCrash/CCircleDay.html

  23. Sirignano, J.A.: Deep learning for limit order books. Quant. Finance 19(4), 549–570 (2019). https://doi.org/10.1080/14697688.2018.1546053

    Article  MathSciNet  MATH  Google Scholar 

  24. Tashiro, D., Matsushima, H., Izumi, K., Sakaji, H.: Encoding of high-frequency order information and prediction of short-term stock price by deep learning. Quant. Finance 19(9), 1499–1506 (2019). https://doi.org/10.1080/14697688.2019.1622314

    Article  MathSciNet  MATH  Google Scholar 

  25. Torii, T., Izumi, K., Yamada, K.: Shock transfer by arbitrage trading: analysis using multi-asset artificial market. Evolut. Instit. Econ. Rev. 12(2), 395–412 (2015). https://doi.org/10.1007/s40844-015-0024-z

    Article  Google Scholar 

  26. Tsantekidis, A., Passalis, N., Tefas, A., Kanniainen, J., Gabbouj, M., Iosifidis, A.: Using deep learning to detect price change indications in financial markets. In: proceedings of the 25th european signal processing conference, pp. 2580–2584 (2017). https://doi.org/10.23919/EUSIPCO.2017.8081663

  27. Uno, J., Goshima, K., Tobe, R.: Cluster Analysis of Trading Behavior: An Attempt to Extract HFT [in Japanese]. In: The 12th Annual Conference of Japanese Association of Behavioral Economics and Finance (2018)

  28. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., Polosukhin, I.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5999–6009 (2017). arXiv:1706.03762

  29. Wang, J., Sun, T., Liu, B., Cao, Y., Zhu, H.: CLVSA: A convolutional LSTM based variational sequence-to-sequence model with attention for predicting trends of financial markets. In: proceedings of the twenty-Eighth international joint conference on artificial intelligence (IJCAI-19), pp. 3705–3711 (2019). https://doi.org/10.24963/ijcai.2019/514

  30. Zhang, L., Aggarwal, C., Qi, G.J.: Stock price prediction via discovering multi-Frequency trading patterns. In: proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining, 2141–2149 (2017). https://doi.org/10.1145/3097983.3098117

Download references

Acknowledgements

We thank the Japan Exchange Group, Inc. for providing the data. This research was supported by MEXT via Exploratory Challenges on Post-K computer (study on multilayered multiscale space-time simulations for social and economic phenomena) and JSPS KAKENHI Grant Number JP 21J20074 (Grant-in-Aid for JSPS Fellows). This research also used the computational resources of the HPCI system provided by the Information Technology Center at The University of Tokyo, and the Joint Center for Advanced High Performance Computing (JCAHPC) through the HPCI System Research Project (Project ID: hp190150).

Author information

Authors and Affiliations

  1. School of Engineering, The University of Tokyo, 7-3-1, Hongo, Bunkyo-ku, Tokyo, 113-8656, Japan

    Masanori Hirano, Kiyoshi Izumi & Hiroki Sakaji

Authors
  1. Masanori Hirano
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kiyoshi Izumi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hiroki Sakaji
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Masanori Hirano.

Ethics declarations

Conflicts of interest

The authors have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hirano, M., Izumi, K. & Sakaji, H. STBM+: Advanced Stochastic Trading Behavior Model for Financial Markets using Residual Blocks or Transformers. New Gener. Comput. 40, 7–24 (2022). https://doi.org/10.1007/s00354-021-00145-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00354-021-00145-z

Keywords

Mathematics Subject Classification

Search

Navigation