Skip to main content
SpringerLink
Log in

Deep Learning for Multi-factor Models in Regional and Global Stock Markets

  • Conference paper
  • First Online:
New Frontiers in Artificial Intelligence (JSAI-isAI 2019)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 12331))

Included in the following conference series:

Abstract

Many studies have been undertaken with machine learning techniques to predict stock returns in terms of time-series prediction. However, from the viewpoint of the cross-sectional prediction with machine learning techniques, there are no examples that verify its profitability in regional and global stock markets. This paper implements deep learning for multi-factor models to predict stock returns in the cross-section in these stock markets and investigates the performance of the method. Our results show that deep neural networks generally outperform representative machine learning models all over the world. These results indicate that deep learning shows promise as a skillful machine learning method to predict stock returns in the cross-section.

Although deep learning performs quite well, it has significant disadvantages such as a lack of transparency and limitations to the interpretability of the prediction. Then, we present the application of layer-wise relevance propagation (LRP) to decompose attributes of the predicted return. By applying LRP to each stock and averaging them in a portfolio, we can determine which factor contributes to prediction. We illustrate which factor contributes to prediction in regional and global stock markets.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    The rate of decline from the maximum return is called drawdown. The case with the largest drawdown is called the maximum drawdown and is usually used as a risk measurement.

References

  1. Abadi, M., et al.: TensorFlow: a system for large-scale machine learning. In: 12th \(\{\)USENIX\(\}\) Symposium on Operating Systems Design and Implementation (\(\{\)OSDI\(\}\) 16), pp. 265–283 (2016)

    Google Scholar 

  2. Abe, M., Nakayama, H.: Deep learning for forecasting stock returns in the cross-section. In: Phung, D., Tseng, V.S., Webb, G.I., Ho, B., Ganji, M., Rashidi, L. (eds.) PAKDD 2018. LNCS (LNAI), vol. 10937, pp. 273–284. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-93034-3_22

    Chapter  Google Scholar 

  3. Anava, O., Levy, K.: k*-nearest neighbors: from global to local. In: Advances in Neural Information Processing Systems, pp. 4916–4924 (2016)

    Google Scholar 

  4. Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.R., Samek, W.: On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PloS one 10(7), e0130140 (2015)

    Article  Google Scholar 

  5. Bahrammirzaee, A.: A comparative survey of artificial intelligence applications in finance: artificial neural networks, expert system and hybrid intelligent systems. Neural Comput. Appl. 19(8), 1165–1195 (2010). https://doi.org/10.1007/s00521-010-0362-z

    Article  Google Scholar 

  6. Bollerslev, T.: Generalized autoregressive conditional heteroskedasticity. J. Econom. 31(3), 307–327 (1986)

    Article  MathSciNet  MATH  Google Scholar 

  7. Cavalcante, R.C., Brasileiro, R.C., Souza, V.L., Nobrega, J.P., Oliveira, A.L.: Computational intelligence and financial markets: a survey and future directions. Expert Syst. Appl. 55, 194–211 (2016)

    Article  Google Scholar 

  8. Chen, J.: SVM application of financial time series forecasting using empirical technical indicators. In: 2010 International Conference on Information, Networking and Automation (ICINA), vol. 1, pp. V1–77. IEEE (2010)

    Google Scholar 

  9. Chen, T., Guestrin, C.: XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785–794. ACM (2016)

    Google Scholar 

  10. Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995). https://doi.org/10.1007/BF00994018

    Article  MATH  Google Scholar 

  11. Cover, T.M., Hart, P., et al.: Nearest neighbor pattern classification. IEEE Trans. Inf. Theory 13(1), 21–27 (1967)

    Article  MATH  Google Scholar 

  12. Engle, R.F., Ledoit, O., Wolf, M.: Large dynamic covariance matrices. J. Bus. Econ. Stat. 37(2), 363–375 (2019)

    Article  MathSciNet  Google Scholar 

  13. Fama, E.F., French, K.R.: The cross-section of expected stock returns. J. Finance 47(2), 427–465 (1992)

    Article  Google Scholar 

  14. Fama, E.F., French, K.R.: Common risk factors in the returns on stocks and bonds. J. Financ. Econ. 33(1), 3–56 (1993)

    Article  MATH  Google Scholar 

  15. Hamilton, J.D.: Time Series Analysis, vol. 2. Princeton University Press, Princeton (1994)

    MATH  Google Scholar 

  16. Harvey, C.R., Liu, Y., Zhu, H.:...and the cross-section of expected returns. Rev. Financ. Stud. 29(1), 5–68 (2016)

    Google Scholar 

  17. Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)

  18. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)

  19. Kristoufek, L., Vosvrda, M.: Measuring capital market efficiency: global and local correlations structure. Physica A 392(1), 184–193 (2013)

    Article  Google Scholar 

  20. Levin, A.E.: Stock selection via nonlinear multi-factor models. In: Advances in Neural Information Processing Systems, pp. 966–972 (1996)

    Google Scholar 

  21. Memmel, C.: Performance hypothesis testing with the Sharpe ratio. Financ. Lett. 1(1), 21–23 (2003)

    Google Scholar 

  22. Nakagawa, K., Imamura, M., Yoshida, K.: Risk-based portfolios with large dynamic covariance matrices. Int. J. Financ. Stud. 6(2), 52 (2018)

    Article  Google Scholar 

  23. Nakagawa, K., Imamura, M., Yoshida, K.: Stock price prediction with fluctuation patterns using indexing dynamic time warping and \(k^*\)-nearest neighbors. In: Arai, S., Kojima, K., Mineshima, K., Bekki, D., Satoh, K., Ohta, Y. (eds.) JSAI-isAI 2017. LNCS (LNAI), vol. 10838, pp. 97–111. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-93794-6_7

    Chapter  Google Scholar 

  24. Nakagawa, K., Imamura, M., Yoshida, K.: Stock price prediction using k-medoids clustering with indexing dynamic time warping. Electron. Commun. Jpn 102(2), 3–8 (2019)

    Article  Google Scholar 

  25. Nakagawa, K., Ito, T., Abe, M., Izumi, K.: Deep recurrent factor model: interpretable non-linear and time-varying multi-factor model. arXiv preprint arXiv:1901.11493 (2019)

  26. Nakagawa, K., Uchida, T., Aoshima, T.: Deep factor model. In: Alzate, C., et al. (eds.) MIDAS/PAP -2018. LNCS (LNAI), vol. 11054, pp. 37–50. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-13463-1_3

    Chapter  Google Scholar 

  27. Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12(Oct), 2825–2830 (2011)

    MathSciNet  MATH  Google Scholar 

  28. Rumelhart, D.E., Hinton, G.E., Williams, R.J., et al.: Learning representations by back-propagating errors. Cogn. Model. 5(3), 1 (1988)

    MATH  Google Scholar 

  29. Vanstone, B., Finnie, G., Hahn, T.: Creating trading systems with fundamental variables and neural networks: the Aby case study. Math. Comput. Simul. 86, 78–91 (2012)

    Article  MathSciNet  Google Scholar 

  30. Zoonekynd, V., LeBinh, K., Lau, A., Sambatur, H.: Machine learning in finance. In: Deutsche Bank Markets Research Report (2016). http://www.fullertreacymoney.com/system/data/files/PDFs/2017/October/20th/(Deutsche)%20Machine%20Learning%20in%20Finance.pdf

Download references

Author information

Authors and Affiliations

  1. Nomura Assset Management Co., Ltd., Tokyo, Japan

    Masaya Abe & Kei Nakagawa

Authors
  1. Masaya Abe
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kei Nakagawa
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Masaya Abe .

Editor information

Editors and Affiliations

  1. The University of Electro-Communications, Tokyo, Japan

    Maki Sakamoto

  2. Tokyo Institute of Technology, Tokyo, Japan

    Naoaki Okazaki

  3. Keio University, Tokyo, Japan

    Koji Mineshima

  4. National Institute of Informatics, Tokyo, Japan

    Ken Satoh

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Abe, M., Nakagawa, K. (2020). Deep Learning for Multi-factor Models in Regional and Global Stock Markets. In: Sakamoto, M., Okazaki, N., Mineshima, K., Satoh, K. (eds) New Frontiers in Artificial Intelligence. JSAI-isAI 2019. Lecture Notes in Computer Science(), vol 12331. Springer, Cham. https://doi.org/10.1007/978-3-030-58790-1_6

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-58790-1_6

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-58789-5

  • Online ISBN: 978-3-030-58790-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation