Advertisement

Deep Factor Model

Explaining Deep Learning Decisions for Forecasting Stock Returns with Layer-Wise Relevance Propagation
  • Kei NakagawaEmail author
  • Takumi Uchida
  • Tomohisa Aoshima
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11054)

Abstract

We propose to represent a return model and risk model in a unified manner with deep learning, which is a representative model that can express a nonlinear relationship. Although deep learning performs quite well, it has significant disadvantages such as a lack of transparency and limitations to the interpretability of the prediction. This is prone to practical problems in terms of accountability. Thus, we construct a multifactor model by using interpretable deep learning. We implement deep learning as a return model to predict stock returns with various factors. Then, we present the application of layer-wise relevance propagation (LRP) to decompose attributes of the predicted return as a risk model. By applying LRP to an individual stock or a portfolio basis, we can determine which factor contributes to prediction. We call this model a deep factor model. We then perform an empirical analysis on the Japanese stock market and show that our deep factor model has better predictive capability than the traditional linear model or other machine learning methods. In addition, we illustrate which factor contributes to prediction.

Keywords

Deep factor model Deep learning Layer-wise relevance propagation 

References

  1. 1.
    Abadi, M., et al.: TensorFlow: a system for large-scale machine learning. In: OSDI, vol. 16, pp. 265–283 (2016)Google Scholar
  2. 2.
    Abe, M., Nakayama, H.: Deep learning for forecasting stock returns in the cross-section. In: Pacific-Asia Conference on Knowledge Discovery and Data Mining (2018)CrossRefGoogle Scholar
  3. 3.
    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)CrossRefGoogle Scholar
  4. 4.
    Blitz, D.C., Van Vliet, P.: The volatility effect: lower risk without lower return. J. Portfolio Manag (2007). CiteseerGoogle Scholar
  5. 5.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)CrossRefGoogle Scholar
  6. 6.
    Carhart, M.M.: On persistence in mutual fund performance. J. Financ. 52(1), 57–82 (1997)CrossRefGoogle Scholar
  7. 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)CrossRefGoogle Scholar
  8. 8.
    Drucker, H., Burges, C.J., Kaufman, L., Smola, A.J., Vapnik, V.: Support vector regression machines. In: Advances in Neural Information Processing Systems, pp. 155–161 (1997)Google Scholar
  9. 9.
    Fama, E.F., French, K.R.: The cross-section of expected stock returns. J. Financ. 47(2), 427–465 (1992)CrossRefGoogle Scholar
  10. 10.
    Fama, E.F., French, K.R.: Size, value, and momentum in international stock returns. J. Financ. Econ. 105(3), 457–472 (2012)CrossRefGoogle Scholar
  11. 11.
    Goodfellow, I., Bengio, Y., Courville, A., Bengio, Y.: Deep Learning, vol. 1. MIT Press, Cambridge (2016)zbMATHGoogle Scholar
  12. 12.
    Griffin, J.M.: Are the Fama and French factors global or country specific? Rev. Financ. Stud. 15(3), 783–803 (2002)CrossRefGoogle Scholar
  13. 13.
    Grinold, R.C., Kahn, R.N.: Active portfolio management (2000)Google Scholar
  14. 14.
    Harvey, C.R., Liu, Y., Zhu, H.: \(\ldots \) and the cross-section of expected returns. Rev. Financ. Stud. 29(1), 5–68 (2016)CrossRefGoogle Scholar
  15. 15.
    Jurczenko, E.: Risk-Based and Factor Investing. Elsevier, Amsterdam (2015)Google Scholar
  16. 16.
    Kinga, D., Adam, J.B.: A method for stochastic optimization. In: International Conference on Learning Representations (ICLR), vol. 5 (2015)Google Scholar
  17. 17.
    Kubota, K., Takehara, H.: Does the Fama and French five-factor model work well in Japan? Int. Rev. Financ. 18(1), 137–146 (2018)CrossRefGoogle Scholar
  18. 18.
    Levin, A.E.: Stock selection via nonlinear multi-factor models. In: Advances in Neural Information Processing Systems, pp. 966–972 (1996)Google Scholar
  19. 19.
    McLean, R.D., Pontiff, J.: Does academic research destroy stock return predictability? J. Financ. 71(1), 5–32 (2016)CrossRefGoogle Scholar
  20. 20.
    Merton, R.C.: An intertemporal capital asset pricing model. Econometrica: J. Econometric Soc. 867–887 (1973)MathSciNetCrossRefGoogle Scholar
  21. 21.
    Novy-Marx, R.: The other side of value: the gross profitability premium. J. Financ. Econ. 108(1), 1–28 (2013)CrossRefGoogle Scholar
  22. 22.
    Pedregosa, F., et al.: Scikit-Learn: machine learning in Python. J. Mach. Learn. Res. 12(Oct), 2825–2830 (2011)MathSciNetzbMATHGoogle Scholar
  23. 23.
    Rosenberg, B., McKibben, W.: The prediction of systematic and specific risk in common stocks. J. Financ. Quant. Anal. 8(2), 317–333 (1973)CrossRefGoogle Scholar
  24. 24.
    Ross, S.A., et al.: The arbitrage theory of capital asset pricing. J. Econ. Theory 13(3), 341–360 (1976)MathSciNetCrossRefGoogle Scholar
  25. 25.
    Subrahmanyam, A.: The cross-section of expected stock returns: what have we learnt from the past twenty-five years of research? Eur. Financ. Manag. 16(1), 27–42 (2010)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Nomura Asset Management Ltd.Chuo-kuJapan
  2. 2.Fujitsu Cloud Technologies LimitedShinjuku-kuJapan
  3. 3.Graduate School of Business SciencesUniversity of TsukubaTsukubaJapan
  4. 4.Department of Risk EngineeringUniversity of TsukubaTsukubaJapan

Personalised recommendations