Advertisement

A novel (U)MIDAS-SVR model with multi-source market sentiment for forecasting stock returns

  • Qifa Xu
  • Liukai Wang
  • Cuixia JiangEmail author
  • Yezheng Liu
Original Article
  • 13 Downloads

Abstract

From the point view of behavioral finance, market sentiment plays an important role in forecasting stock returns. How to accurately measure the impact of market sentiment is a challenge work. Two issues on nonlinear relationship and mixed-frequency data have to be addressed. To this end, we introduce methods of mixed-frequency data into SVRs and develop a novel (U)MIDAS-SVR model. It can be estimated by solving the Lagrange duality technique of quadratic programming. We then apply the (U)MIDAS-SVR model to predict weekly returns of SHSE and SZSE in China using the mixed-frequency market sentiment as covariates. The empirical results show that the (U)MIDAS-SVR model is promising and MIDAS-SVR is superior to those competing models in terms of MAE and RMSE. In addition, we design seven scenarios by considering different data source combinations and find that the multi-source market sentiment is helpful to improve forecasting performance on stock returns.

Keywords

Mixed-frequency data Support vector regression (U)MIDAS-SVR Market sentiment 

Notes

Acknowledgements

The authors are grateful to the Editor-in-Chief, the Associate Editor, and two anonymous referees for their helpful comments and constructive guidance. This work was supported by the National Natural Science Foundation of PR China (71671056, 91846201).

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

References

  1. 1.
    Edmans A, Jayaraman S, Schneemeier J (2017) The source of information in prices and investment-price sensitivity. J Financ Econ 126(1):74–96CrossRefGoogle Scholar
  2. 2.
    Fama EF (1965) The behavior of stock-market prices. J Bus 38(1):34–105CrossRefGoogle Scholar
  3. 3.
    Liu X, Ye Q (2016) The different impacts of news-driven and self-initiated search volume on stock prices. Inf Manag 53(8):997–1005CrossRefGoogle Scholar
  4. 4.
    Oliveira N, Cortez P, Areal N (2016) Stock market sentiment lexicon acquisition using microblogging data and statistical measures. Decis Support Syst 85:62–73CrossRefGoogle Scholar
  5. 5.
    Zakoian JM (1994) Threshold heteroskedastic models. J Econ Dyn Control 18(5):931–955CrossRefzbMATHGoogle Scholar
  6. 6.
    Bonhomme S, Jochmans K, Robin J (2017) Nonparametric estimation of non-exchangeable latent-variable models. J Econom 201(2):237–248MathSciNetCrossRefzbMATHGoogle Scholar
  7. 7.
    Langrock R, Kneib T, Glennie R, Michelot T (2017) Markov-switching generalized additive models. Stat Comput 27(1):259–270MathSciNetCrossRefzbMATHGoogle Scholar
  8. 8.
    Canepa A, Chini E (2016) Dynamic asymmetries in house price cycles: a generalized smooth transition model. J Empir Finance 37:91–103CrossRefGoogle Scholar
  9. 9.
    Luo L, Chen X (2013) Integrating piecewise linear representation and weighted support vector machine for stock trading signal prediction. Appl Soft Comput 13(2):806–816CrossRefGoogle Scholar
  10. 10.
    Gawali DD, Zidna A, Nataraj PSV (2017) Algorithms for unconstrained global optimization of nonlinear (polynomial) programming problems: the single and multi-segment polynomial B-spline approach. Comput Oper Res 87:205–220MathSciNetCrossRefzbMATHGoogle Scholar
  11. 11.
    Song Y, Jian L, Lin L (2016) Robust exponential squared loss-based variable selection for high-dimensional single-index varying-coefficient model. J Comput Appl Math 308:330–345MathSciNetCrossRefzbMATHGoogle Scholar
  12. 12.
    Medovikov I (2016) When does the stock market listen to economic news? New evidence from copulas and news wires. J Bank Finance 65:27–40CrossRefGoogle Scholar
  13. 13.
    Jabbar S, Hamed R, Alwan A (2018) The potential of nonparametric model in foundation bearing capacity prediction. Neural Comput Appl 30(10):3235–3241CrossRefGoogle Scholar
  14. 14.
    Azcarraga A, Setiono R (2018) Neural network rule extraction for gaining insight into the characteristics of poverty. Neural Comput Appl 30(9):2795–2806CrossRefGoogle Scholar
  15. 15.
    Xu Q, Liu X, Jiang C, Yu K (2016) Quantile autoregression neural network model with applications to evaluating value at risk. Appl Soft Comput 46:1–12CrossRefGoogle Scholar
  16. 16.
    Mu Y, Liu X, Wang L (2018) A Pearson’s correlation coefficient based decision tree and its parallel implementation. Inf Sci 435:40–58MathSciNetCrossRefGoogle Scholar
  17. 17.
    Xie X (2018) Improvement on projection twin support vector machine. Neural Comput Appl 30(2):371–387CrossRefGoogle Scholar
  18. 18.
    Kao L, Chiu Ch, Lu Chi, Yang J (2013) Integration of nonlinear independent component analysis and support vector regression for stock price forecasting. Neurocomputing 99:534–542CrossRefGoogle Scholar
  19. 19.
    Peng Y, Albuquerque P, Camboim d, Jader M, Padula A, Montenegro MR (2018) The best of two worlds: forecasting high-frequency volatility for cryptocurrencies and traditional currencies with support vector regression. Expert Syst Appl 97:177–192CrossRefGoogle Scholar
  20. 20.
    Pan X, Pang X, Wang H, Xu Y (2018) A safe screening based framework for support vector regression. Neurocomputing 287:163–172CrossRefGoogle Scholar
  21. 21.
    Narayan P, Sharma S (2015) Does data frequency matter for the impact of forward premium on spot exchange rate? Int Rev Financ Anal 39:45–53CrossRefGoogle Scholar
  22. 22.
    Pettenuzzo D, Timmermann A, Valkanov R (2016) A MIDAS approach to modeling first and second moment dynamics. J Econom 193:315–334MathSciNetCrossRefzbMATHGoogle Scholar
  23. 23.
    Bams D, Blanchard G, Honarvar I, Lehnert T (2017) Does oil and gold price uncertainty matter for the stock market? J Empir Finance 44:270–285CrossRefGoogle Scholar
  24. 24.
    Ghysels E, Sinko A, Valkanov R (2007) MIDAS regressions: further results and new directions. Econom Rev 26(1):53–90MathSciNetCrossRefzbMATHGoogle Scholar
  25. 25.
    Xu Q, Zhuo X, Jiang C, Liu Y (2019) An artificial neural network for mixed frequency data. Expert Syst Appl 118:127–139CrossRefGoogle Scholar
  26. 26.
    Foroni C, Marcellino M, Schumacher C (2015) Unrestricted mixed data sampling (MIDAS): MIDAS regressions with unrestricted lag polynomials. J R Stat Soc Ser A 178(1):57–82MathSciNetCrossRefGoogle Scholar
  27. 27.
    Ramiah V, Xu X, Moosa IA (2015) Neoclassical finance, behavioral finance and noise traders: a review and assessment of the literature. Int Rev Financ Anal 41:89–100CrossRefGoogle Scholar
  28. 28.
    Gao B, Yang Chun (2017) Forecasting stock index futures returns with mixed-frequency sentiment. Int Rev Econ Finance 49:69–83CrossRefGoogle Scholar
  29. 29.
    Shen D, Zhang Y, Xiong X, Zhang W (2017) Baidu index and predictability of Chinese stock returns. Financ Innov 3(1):4–4CrossRefGoogle Scholar
  30. 30.
    Thenmozhi M, Sarath CG (2016) Forecasting stock returns based on information transmission across global markets using support vector machines. Neural Comput Appl 27(4):805–824CrossRefGoogle Scholar
  31. 31.
    Shynkevich Y, McGinnity TM, Coleman SA, Belatreche A, Li Y (2017) Forecasting price movements using technical indicators: investigating the impact of varying input window length. Neurocomputing 264(15):71–88CrossRefGoogle Scholar
  32. 32.
    Yang C, Zhou L (2015) Investor trading behavior, investor sentiment and asset prices. N Am J Econ Finance 34:42–62CrossRefGoogle Scholar
  33. 33.
    Yang C, Gao B (2014) Intraday futures patterns and volume–volatility relationships: the German evidence. Rev Manag Sci 8(1):29–61CrossRefGoogle Scholar
  34. 34.
    Yang C, Gao B (2014) The term structure of sentiment effect in stock index futures market. N Am J Econ Finance 30:171–182CrossRefGoogle Scholar
  35. 35.
    Pan Y, Xiao Z, Wang X, Yang D (2017) A multiple support vector machine approach to stock index forecasting with mixed frequency sampling. Knowl Based Syst 122:90–102CrossRefGoogle Scholar
  36. 36.
    Xu Q, Zhang J, Jiang C, Huang X, He Y (2015) Weighted quantile regression via support vector machine. Expert Syst Appl 42(13):5441–5451CrossRefGoogle Scholar
  37. 37.
    Ma X, Liu Z (2018) Predicting the oil production using the novel multivariate nonlinear model based on Arps decline model and kernel method. Neural Comput Appl 29(2):579–591CrossRefGoogle Scholar
  38. 38.
    Dhamija AK, Bhalla VK (2011) Exchange rate forecasting: comparison of various architectures of neural networks. Neural Comput Appl 20(3):355–363CrossRefGoogle Scholar
  39. 39.
    Jiang C, Jiang M, Xu Q, Huang X (2017) Expectile regression neural network model with applications. Neurocomputing 247:73–86CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  1. 1.School of ManagementHefei University of TechnologyHefeiPeople’s Republic of China
  2. 2.Key Laboratory of Process Optimization and Intelligent Decision-MakingMinistry of EducationHefeiPeople’s Republic of China

Personalised recommendations