A Combined Model for Time Series Prediction in Financial Markets

  • Hongbo Sun
  • Chenkai GuoEmail author
  • Jing Xu
  • Jingwen Zhu
  • Chao Zhang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10988)


Time series prediction is not easy to achieve high accuracy. non-linear and unstable characteristics make the time series prediction difficult. The variety of dataset make the prediction result debatable. In order to solve this problem, in this paper we propose a deep learning prediction method based on decomposition, reconstruction and combination, which combines ways of communication field. The model is decomposed by Empirical Mode Decomposition, Principal Component Analysis and Long Short-Term Memory networks (EPL below). And also, the proposed interval EPL (IEPL below) improve and consummate the EPL model. The EPL and IEPL experiment results will bring average 5% higher accuracy than that of existing research.


Time series prediction Deep learning EPL IEPL 



This research work here is supported by the Science and Technology Planning Project of Tianjin (Grant No. 17JCZDJC30700 and 17YFZCGX00610).


  1. 1.
    Hu, J., Zhang, L., Cai, Z., et al.: An intelligent fault diagnosis system for process plant using a functional HAZOP and DBN integrated methodology. Proc. Eng. Appl. Artif. Intell. 45, 119–135 (2015)CrossRefGoogle Scholar
  2. 2.
    Cao, L., Huang, W., Sun, F.: Building feature space of extreme learning machine with sparse denoising stacked-autoencoder. Neurocomputing 174(A), 60–71 (2016)CrossRefGoogle Scholar
  3. 3.
    Sezer, O.B., Ozbayoglu, M., Dogdu, E.: A Deep neural-network based stock trading system based on evolutionary optimized technical analysis parameters. Proc. Comput. Sci. 114, 473–480 (2017)CrossRefGoogle Scholar
  4. 4.
    Furlaneto, D.C., Oliveira, L.S., Menotti, D., et al.: Bias effect on predicting market trends with EMD. Expert Syst. Appl. 82, 16–29 (2017)Google Scholar
  5. 5.
    Lahmiri, S.: Wavelet low- and high-frequency components as features for predicting stock prices with backpropagation neural networks. J. King Saud Univ. Comput. Inf. Sci. 26(2), 218–227 (2014)Google Scholar
  6. 6.
    Ismail, A., Jeng, D.-S., Zhang, L.L.: An optimized product-unit neural network with a novel PSO-BP hybrid training algorithm: applications to load-deformation analysis of axially loaded piles. Eng. Appl. Artif. Intell. 26(10), 2305–2314 (2013)CrossRefGoogle Scholar
  7. 7.
    Pérez-Ortiz, J., Gers, F.A., Eck, D., et al.: Kalman filters improve LSTM network performance in problems unsolvable by traditional recurrent nets. Neural Netw. 16(2), 241–250 (2003)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.College of Computer and Control of EngineeringNankai UniversityTianjinChina

Personalised recommendations