Forecasting Stock Price Index Volatility with LSTM Deep Neural Network

Conference paper
Part of the Springer Proceedings in Business and Economics book series (SPBE)

Abstract

In strong noisy financial market, accurate volatility forecasting is the core task in risk management. In this paper, we apply GARCH model and a LSTM model to predict the stock index volatility. Instead of historical volatility, we select extreme value volatility of Shanghai Compos stock price index to conduct empirical study. By comparing the values of four types of loss functions, we illustrate that LSTM model has a better predicting effect.

Keywords

LSTM Volatility forecasting Extreme value volatility GARCH 

References

  1. 1.
    Bollerslev, T. (1986). Generalized autoregressive conditional heteroscedasticity. Journal of Econometrics, 31, 307–327.CrossRefGoogle Scholar
  2. 2.
    Engle, R. F. (1982). Autoregressive conditional heteroscedasticity with estimator of the variance of United Kingdom inflation. Econometrica, 50(4), 987–1008.CrossRefGoogle Scholar
  3. 3.
    Tray, R. S. (2012). Analysis of financial time series. Bei Jing: Posts & Telecom Press.Google Scholar
  4. 4.
    Cheng Chang-Pin, Chen Qiang, Jinag Yong-Sheng. (2012). Stock price forecasting based on ARIMA-SVM combination model. Computer simulation, 06, 343–346.Google Scholar
  5. 5.
    Li, L. (2017). An empirical study on WTI index based on ARIMA-GARCH model. Value Engineering, 02, 38–39.Google Scholar
  6. 6.
    Huang, Z., Chen, H., Hsu, C., Chen, W., & Wu, S. (2004). Credit rating analysis with support vector machines and neural networks, a market comparative study. Decision Support Systems, 37, 543.CrossRefGoogle Scholar
  7. 7.
    Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9, 1735–1780.CrossRefGoogle Scholar
  8. 8.
    Gers, F., Shmidhuber, J., & Cummmins, F. (2000). Learning to forget: Continual prediction with LSTM. Neural Computation, 12, 2451–2471.CrossRefGoogle Scholar
  9. 9.
    Kang, S., Qian, X., & Meng, H. (2013). Multi-distribution deep belief network for speech synthesis[C]//Acoustics, Speech and Signal Processing (ICASSP), 2013 I.E. international conference on IEEE, 8012–8016.Google Scholar
  10. 10.
    Sundermeyer, M., Schluter, R., & Ney, H. (2010). LSTM neural networks for language modeling, International conferenceon spoken language processing, inter speech.Google Scholar
  11. 11.
    Graves, A., Mohamed, A., & Hinton, G. (2013). Speech recognition with deep recurrent neural networks. Acoustics, Speech and Signal Processing (ICASSP), 10, 6645–6649.Google Scholar
  12. 12.
    Parkinson, M. (1980). The extreme value method for estimating the variance of the rate of return. Journal of Business, 53, 61.CrossRefGoogle Scholar
  13. 13.
    Hansen, P. R. (2005). A test for superior predictive ability. Journal of Business and Economic Statistics, 23(4), 365–380.Google Scholar
  14. 14.
    Chollet, F. (2015). Keras, Https://github.com/keras-team/keras.Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.School of Science, Changchun University of Science and TechnologyChangchunChina

Personalised recommendations