A LSTM Approach for Sales Forecasting of Goods with Short-Term Demands in E-Commerce

  • Yu-Sen ShihEmail author
  • Min-Huei LinEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11431)


This study proposed a model to forecast short-term goods demand in E-commerce context. The model integrated LSTM approach with sentiment analysis of consumers’ comments. In the training stage, the sales figures and comments crawled from “” were preprocessed, and the sentiment rating of comments were analyzed for “positive”, “negative” and confidence. The LSTM model was trained to learn the prediction of future value according to the time-series sequence of sales and sentiment rating of comments. Due to the characteristics of short-term goods, there are not enough history data to evaluate cyclic and periodic variation, so the decision makers have to react to market conditions and take appropriate actions as soon as possible. It also suggested that to adjust the weight of sentiment rating appropriately could further improve the forecasting accuracy. The study fulfilled the goal for supporting them to make use of minimal trading data to achieve maximal predictive accuracy. The results demonstrated that the proposed LSTM approach performed high-level accuracy for sales forecasting of goods with short-term demands.


LSTM Short-term goods demands Sales forecasting Sentiment analysis 


  1. 1.
    Chen, A.Y.: Using the text mining and sentiment analysis technology to develop the store commodity evaluation module. Master’s thesis of Graduate Institute of Information Management, 48 p. National Taipei University, Taipei (2017)Google Scholar
  2. 2.
    Chniti, G., Bakir, H., Zaher, H.: E-commerce time series forecasting using LSTM neural network and support vector regression. In: Proceedings of the International Conference on Big Data and Internet of Thing - BDIOT2017, pp. 80–84. ACM (2017)Google Scholar
  3. 3.
    Fan, Y.N., Huang, H.W., Chen, C.C.: A solution for sales forecasts of fashion products based on electronic word-of-mouth. J. Inf. Manag. 19, 27–50 (2012)Google Scholar
  4. 4.
    Fan, Z.P., Che, Y.J., Chen, Z.Y.: Product sales forecasting using online reviews and historical sales data: a method combining the Bass model and sentiment analysis. J. Bus. Res. 74, 90–100 (2017). Scholar
  5. 5.
    Feldman, R.: Techniques and applications for sentiment analysis: the main applications and challenges of one of the hottest research areas in computer science. Commun. ACM 56(4), 82–89 (2013). Scholar
  6. 6.
    Goyal, A., Kumar, R., Kulkarni, S., Krishnamurthy, S., Vartak, M.: A solution to forecast demand using long short-term memory recurrent neural networks for time series forecasting. In: 2018 Midwest Decision Sciences Institute Conference, pp. 1–18 (2018)Google Scholar
  7. 7.
    Kahn, K.B.: Benchmarking sales forecasting performance measure. J. Bus. Forecast. Methods Syst. 17(4), 19–23 (1998)Google Scholar
  8. 8.
    Kadam, S., Apte, M.D.: A survey on short life cycle time series forecasting. Int. J. Appl. Innov. Eng. Manag. 4, 445–449 (2015)Google Scholar
  9. 9.
    Liu, B.: Sentiment analysis and subjectivity. Handb. Nat. Lang. Process. 2, 627–666 (2010)Google Scholar
  10. 10.
    Liu, B.: Sentiment Analysis and Opinion Mining. [Electronic Resource]. Morgan & Claypool, San Rafael (2012)Google Scholar
  11. 11.
    Marshall, P., Dockendorff, M., Ibáñez, S.: A forecasting system for movie attendance. J. Bus. Res. 66(10), 1800–1806 (2013)CrossRefGoogle Scholar
  12. 12.
    Pang, B., Lee, L.: Opinion mining and sentiment analysis. Found. Trends Inf. Retrieval 2(1–2), 1–135 (2008). Scholar
  13. 13.
    Shi, X., Li, F., Bigdeli, A.Z.: An examination of NPD models in the context of business models. J. Bus. Res. 69(7), 2541–2550 (2016)CrossRefGoogle Scholar
  14. 14.
    Shu, L.Z.: Research on sales forecasting methods. Mod. Mark. 7, 80 (2011). Scholar
  15. 15.
    Yang, C.S., Xie, P.Y., Shih, H.P.: Mining consumer knowledge from social media: development of an opinion mining technique. NTU Manag. Rev. 27, 1–28 (2017). Scholar
  16. 16.
    Yu, Q., Wang, K., Strandhagen, J.O., Wang, Y.: Application of long short-term memory neural network to sales forecasting in retail—a case study. In: Wang, K., Wang, Y., Strandhagen, J., Yu, T. (eds.) IWAMA 2017, pp. 11–17. Springer, Singapore (2018). Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Information and Finance ManagementNational Taipei University of TechnologyTaipeiTaiwan
  2. 2.Department of Information ManagementAletheia UniversityNew Taipei CityTaiwan

Personalised recommendations