An Evaluation of Equity Premium Prediction Using Multiple Kernel Learning with Financial Features

  • Argimiro Arratia
  • Lluís A. BelancheEmail author
  • Luis Fábregues


This paper introduces and extensively explores a forecasting procedure based on multivariate dynamic kernels to re-examine—under a non-linear, kernel methods framework—the experimental tests reported by Welch and Goyal (Rev Financ Stud 21(4):1455–1508, 2008) showing that several variables proposed in the finance literature are of no use as exogenous information to predict the equity premium under linear regressions. For this new approach to equity premium forecasting, kernel functions for time series are used with multiple kernel learning (MKL) in order to represent the relative importance of each of the variables. We find that, in general, the predictive capabilities of the MKL models do not improve consistently with the use of some or all of the variables, nor does the predictability by single kernels, as determined by different resampling procedures that we implement and compare. This fact tends to corroborate the instability already observed by Welch and Goyal for the predictive power of exogenous variables, now in a non-linear modelling framework.


Support vector classification Support vector regression Financial time series Multiple kernel learning Kernel functions for time series 



  1. 1.
    Aiolli F, Donini M (2015) EasyMKL: a scalable multiple kernel learning algorithm. Neurocomputing 169:215–224CrossRefGoogle Scholar
  2. 2.
    Ang A, Bekaert G (2007) Stock return predictability: is it there? Rev Financ Stud 20(3):651–707CrossRefGoogle Scholar
  3. 3.
    Bach FR, Lanckriet GR, Jordan MI (2004) Multiple kernel learning, conic duality, and the SMO algorithm. In: Proceedings of the twenty-first international conference on machine learning. ACM, p 6Google Scholar
  4. 4.
    Bergmeir C, Hyndman R, Koo B (2015) A note on the validity of cross-validation for evaluating time series prediction. Department of Econometrics and Business Statistics, Working Paper, ISSN 1440-771XGoogle Scholar
  5. 5.
    Box GEP, Hunter JS, Hunter WG (2005) Statistics for experimenters: design, innovation, and discovery, 2nd edn. Wiley, New York ISBN: 978-0-471-71813-0zbMATHGoogle Scholar
  6. 6.
    Campbell JY, Shiller RJ (1988) The dividend-price ratio and expectations of future dividends and discount factors. Rev Financ Stud 1:195–228CrossRefGoogle Scholar
  7. 7.
    Campbell JY, Thompson SB (2008) Predicting excess stock returns out of sample: can anything beat the historical average? Rev Financ Stud 21(4):1509–1531CrossRefGoogle Scholar
  8. 8.
    Chang C, Lin C (2001) Training \(\nu \)-support vector classifiers: theory and algorithms. Neural Comput 13(9):2119–2147CrossRefzbMATHGoogle Scholar
  9. 9.
    Cho Y, Saul L (2009) Kernel methods for deep learning. Adv Neural Inf Process Syst 22:342–350Google Scholar
  10. 10.
    Cochrane JH (1992) Explaining the variance of price-dividend ratios. Rev Financ Stud 5:243–280CrossRefGoogle Scholar
  11. 11.
    Cochrane JH (2006) The dog that did not bark: a defense of return predictability. Rev Financ Stud 21:1533–1575CrossRefGoogle Scholar
  12. 12.
    Cochrane JH (2011) Presidential address: discount rates. J Finance 56(4):1047–1108CrossRefGoogle Scholar
  13. 13.
    Cuturi M, Vert J-P, Birkenes Ø, Matsui T (2007) A kernel for time series based on global alignments. In: IEEE international conference ICASSP 2007, pp II–413. IEEEGoogle Scholar
  14. 14.
    Cuturi M, Doucet A (2011) Autoregressive kernels for time series. Technical Report arXiv:1101.0673
  15. 15.
    Cuturi M (2011) Fast global alignment kernels. In: Proceedings of the 28th international conference on machine learning (ICML-11), pp 929–936Google Scholar
  16. 16.
    Fábregues L, Arratia A, Belanche LA (2017) Forecasting financial time series with multiple kernel learning. In: Advances in computational intelligence: 14th international work-conference on artificial neural networks, IWANN 2017, CádizGoogle Scholar
  17. 17.
    Fama EF, French KR (1988) Dividend yields and expected stock returns. J Financ Econ 22:3–25CrossRefGoogle Scholar
  18. 18.
    Fletcher Hussain TZ, Shawe-Taylor J (2010) Currency forecasting using multiple kernel learning with financially motivated features. In NIPS 2010 workshop: new directions in multiple kernel learningGoogle Scholar
  19. 19.
    Geler Z, Kurbalija V, Radovanovi M, Ivanovi M (2014) Impact of the Sakoe-Chiba band on the DTW time series distance measure for kNN classification. In: Buchmann R, Kifor CV, Yu J (eds) Knowledge science, engineering and management. KSEM 2014 (LNCS, vol 8793). SpringerGoogle Scholar
  20. 20.
    Hansen LP, Hodrick RJ (1980) Forward exchange rates as optimal predictors of future spot rates: an econometric analysis. J Polit Econ 88:829–853CrossRefGoogle Scholar
  21. 21.
    Kale DC, Gong D, Che Z, Liu Y, Medioni G, Wetzel R, Ross P (2014) An examination of multivariate time series hashing with applications to health care. In: IEEE international conference ICDM 2014, pp 260–269Google Scholar
  22. 22.
    Kothari SP, Shanken J (1997) Book-to-market, dividend yield, and expected market returns: a time-series analysis. J Financ Econ 44(2):169–203CrossRefGoogle Scholar
  23. 23.
    Lettau M, Ludvigson S (2001) Consumption, aggregate wealth, and expected stock returns. J Finance 56(3):815–849CrossRefGoogle Scholar
  24. 24.
    Peña M, Arratia A, Belanche LA (2016) Multivariate dynamic kernels for financial time series forecasting. In: 25th International conference on artificial neural networks, Springer LNCS, vol 9887, pp 336–344Google Scholar
  25. 25.
    Sakoe H, Chiba S (1978) Dynamic programming algorithm optimization for spoken word recognition. IEEE Trans Acoust Speech Signal Process 26(1):43–49CrossRefzbMATHGoogle Scholar
  26. 26.
    Schölkopf B, Smola AJ, Williamson RC, Bartlett PL (2000) New support vector algorithms. Neural Comput 12(5):1207–1245CrossRefGoogle Scholar
  27. 27.
    Shiller RJ (1981) Do stock prices move too much to be justified by subsequent changes in dividends? Am Econ Rev 71:421–436Google Scholar
  28. 28.
    Welch I, Goyal A (2008) A comprehensive look at the empirical performance of equity premium prediction. Rev Financ Stud 21(4):1455–1508CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Computer Science DepartmentUniversitat Politècnica de CatalunyaBarcelonaSpain

Personalised recommendations