Car Sales Prediction Using Gated Recurrent Units Neural Networks with Reinforcement Learning

  • Bowen Zhu
  • Huailong Dong
  • Jing ZhangEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11936)


In this paper, we propose a novel Gated Recurrent Units neural network with reinforcement learning (GRURL) for car sales forecasting. The car sales time series data usually have a small sample size and appear no periodicity. Many previous time series modeling methods, such as linear regression, cannot effectively obtain the best parameter adjustment strategy when fitting the final prediction values. To cope with this challenge and obtain a higher prediction accuracy, in this paper, we combine the GRU with the reinforcement learning, which can use the reward mechanism to obtain the best parameter adjustment strategy while making a prediction. We carefully investigated a real-world time-series car sales dataset in Yancheng City, Jiangsu Province, and built 140 GRURL models for different car models. Compared with the traditional BP, LSTM, and GRU neural networks, the experimental results show that the proposed GRURL model outperforms these traditional deep neural networks in terms of both prediction accuracy and training cost.


Car sales prediction BP LSTM Gated Recurrent Units Reinforcement learning 



This research has been supported by the National Natural Science Foundation of China (NSFC) under grants 91846104 and 61603186, the Natural Science Foundation of Jiangsu Province, China, under grants BK20160843, and the China Postdoctoral Science Foundation under grants 2017T100370.


  1. 1.
    Chatfield, C.: The Analysis of Time Series: An Introduction. Chapman and Hall/CRC, London (2003)zbMATHGoogle Scholar
  2. 2.
    Anderson, T.W.: The Statistical Analysis of Time Series, vol. 19. Wiley, Hoboken (2011)Google Scholar
  3. 3.
    Benkachcha, S., Benhra, J., El Hassani, H.: Causal method and time series forecasting model based on artificial neural network. Int. J. Comput. Appl. 75(7), 37–42 (2013)Google Scholar
  4. 4.
    Kantz, H., Schreiber, T.: Nonlinear Time Series Analysis, vol. 17. Cambridge University Press, Cambridge (2004)zbMATHGoogle Scholar
  5. 5.
    Moody, J., Darken, C.J.: Fast learning in networks of locally-tuned processing units. Neural Comput. 1(2), 281–294 (1989)CrossRefGoogle Scholar
  6. 6.
    Zaremba, W., Sutskever, I., Vinyals, O.: Recurrent neural network regularization. arXiv preprint arXiv:1409.2329 (2014).
  7. 7.
    Jo, T.: VTG schemes for using back propagation for multivariate time series prediction. Appl. Soft Comput. 13(5), 2692–2702 (2013)CrossRefGoogle Scholar
  8. 8.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  9. 9.
    Farahani, D.S., Momeni, M., Amiri, N.S.: Car sales forecasting using artificial neural networks and analytical hierarchy process. In: The 5th International Conference on Data Analytics (DATA ANALYTICS), pp. 57–62. IARIA (2016)Google Scholar
  10. 10.
    Fu, R., Zhang, Z., Li, L.: Using LSTM and GRU neural network methods for traffic flow prediction. In: The 31st Youth Academic Annual Conference of Chinese Association of Automation (YAC), pp. 324–328. IEEE (2017)Google Scholar
  11. 11.
    Duan, Y., Lv, Y., Wang, F.Y.: Travel time prediction with LSTM neural network. In: The 19th IEEE International Conference on Intelligent Transportation Systems (ITSC), pp. 1053–1058. IEEE (2016)Google Scholar
  12. 12.
    Makatjane, K., Moroke, N.: Comparative study of holt-winters triple exponential smoothing and seasonal Arima: forecasting short term seasonal car sales in South Africa. Risk Gov. Control: Financ. Mark. Inst. 6(1), 71–82 (2016)Google Scholar
  13. 13.
    Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)zbMATHGoogle Scholar
  14. 14.
    Chen, X., Qiu, X., Zhu, C., Huang, X.: Gated recursive neural network for Chinese word segmentation. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, pp. 1744–1753 (2015)Google Scholar
  15. 15.
    Cao, J.: Economic globalization and China’s auto industry development. Manag. World 4, 68–76 (2003)Google Scholar
  16. 16.
    Chen, H.: The application of grey theory in sales forecasting and investment decisions. Master thesis, Hefei University of Technology, Anhui, China (2008)Google Scholar
  17. 17.
    Li, X., Zhong, Q., Tong, L.: Hybrid forecasting method for automobile sale. J. Tianjin Univ. ( Soc. Sci. Ed.) 8(3), 175–178 (2006)Google Scholar
  18. 18.
    Giles, C.L., Kuhn, G.M., Williams, R.J.: Dynamic recurrent neural networks: theory and applications. IEEE Trans. Neural Netw. 5(2), 153–156 (1994)CrossRefGoogle Scholar
  19. 19.
    Dayan, P., Balleine, B.W.: Reward, motivation, and reinforcement learning. Neuron 36(2), 285–298 (2002)CrossRefGoogle Scholar
  20. 20.
    Gers, F.A., Eck, D., Schmidhuber, J.: Applying LSTM to time series predictable through time-window approaches. In: Dorffner, G., Bischof, H., Hornik, K. (eds.) ICANN 2001. LNCS, vol. 2130, pp. 669–676. Springer, Heidelberg (2001). Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Computer Science and TechnologyNanjing University of Science and TechnologyNanjingChina

Personalised recommendations