Study on the Inventory Forecasting in Supply Chains Based on Rough Set Theory and Improved BP Neural Network

  • Xuping Wang
  • Yan Shi
  • Junhu Ruan
  • Hongyan Shang
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 4)


It has never stopped to study inventory management problems, and a variety of inventory control models have been proposed, but the existing models have their shortcomings and aren’t suitable to the inventory forecasting in supply chains. According to those shortcomings and the actual situation in supply chains, the paper combined rough set theory and BP neural network to analyze the inventory forecasting in supply chains. The introduction of rough sets cut down the input dimensions of BP neural network, and the neural network algorithm was improved by adding the momentum factor and applying adaptive learning rate. And, according to the inventory data of a manufacturing enterprise in Handan city, the paper proved the validity of the proposed model.


supply chains inventory forecasting rough set theory BP neural network improved algorithm 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Ma, S.-h.: Supply Chain Management. Mechanical Industry Press, Beijing (2000)Google Scholar
  2. 2.
    Harris, F.W.: How Many Parts To Make At Once. The Magazine of Management 10(2), 135–136 (1913)Google Scholar
  3. 3.
    Wilson, R.H.: A Scientific Routine for Stock Control. Harvard Business Review 13, 116–128 (1934)Google Scholar
  4. 4.
    Zhou, Y.-w.: Time Value of Costs of the EOQ model for inventory system. Systems Engineering Theory and Practice 08, 96–102 (1996)Google Scholar
  5. 5.
    Zhang, J.: EOQ-type multi-period changes in the cost of storage strategy. Journal of Systems Engineering 12(01), 96–101 (1997)Google Scholar
  6. 6.
    Luo, B., Xiong, Z.-k., Yang, X.-t.: An EOQ Model Taking Account of the Linear Time-Varying Increasing Demand under Stock Dependent Selling Rate. Chinese Journal of Management Science 10(06), 66–71 (2002)Google Scholar
  7. 7.
    Guo, Q.: Research on the EOQ Model with Losing in Inventory. Systems Engineering 22(07), 17–19 (2004)Google Scholar
  8. 8.
    Flores, B.E., Whybark, D.C.: Implementing multiple criteria AB Canalysis. Journal of Operations Management 7(1&2), 79–85 (1987)CrossRefGoogle Scholar
  9. 9.
    Yang, F.-y., Guo, G.: The Optimization Arithmetic of Safety Storage Based on ABC Classification. Manufacturing Information Engineering of China 33, 83–86 (2004)zbMATHGoogle Scholar
  10. 10.
    Xiao, Y.-y., Chang, W., Guo, W.-h.: A New Algorithm of ABC Inventory Classification Based on the Association Rule. Systems Engineering 26(06), 10–15 (2008)Google Scholar
  11. 11.
    Southard, P.B.: Extending Vendor-managed Inventory into Alternate Supply Chains:A simulation Analysis of Cost and Service Level. University of Nebraska, Nebraska (2001)Google Scholar
  12. 12.
    Xu, K.-a., Chen, X.-j.: An Integrated Vendor-managed-inventory Model Considering the Impact of Advertisement. Operations Research and Management Science 16(06), 21–25 (2006)Google Scholar
  13. 13.
    Li, G.-z., Li, J.-x., Chen, C.-j.: A Vendor-Managed Inventory Model with Partial Backlogging Allowing Shortage. Journal of Qingdao University (Natural Science Edition) 19(04), 61–65 (2006)Google Scholar
  14. 14.
    Partovil, F.Y., Anandarajan, M.: Classifying Invcntory Using an Artificial Neural Network Approach. Computers & Industrial Engineering 41(04), 389–404 (2002)CrossRefGoogle Scholar
  15. 15.
    Wang, D.-x., Shen, Y.-m., Wang, Z.-q.: Applying BP Network to Forecast ERP Safety Goods Stockpile. Journal of Computer Applications 3, 53–55 (2001)CrossRefGoogle Scholar
  16. 16.
    Zhou, B., Zhang, R.-l., Tong, C.-h.: Application of artificial neural networks in forecasting safety goods stockpile of dressing corporations. Computer Engineering and Design 12, 3453–3455 (2005)Google Scholar
  17. 17.
    Luo, B., Huang, W.-j., Yang, S.: Application of BP Neural Networks in Inventory Dynamic Modeling. Journal of Chongqing University (Natural Science Edition) 28(2), 137–140 (2005)Google Scholar
  18. 18.
    Hassanien, A.E.: Intelligent Data Analysis of Breast Cancer Based on Rough Set Theory. International Journal on Artificial Intelligence Tools 12(4), 465–479 (2003)CrossRefGoogle Scholar
  19. 19.
    Gupta, R.: Bayesian methods of forecasting inventory investment. South African Journal of Economics 77(1), 113–126 (2009)CrossRefGoogle Scholar
  20. 20.
    Syntetos, A., Boylan, J.E., Disney, S.M.: Forecasting for inventory planning: a 50-year review. Journal of the Operational Research Society 60, S149–S160 (2009)Google Scholar

Copyright information

© Springer Berlin Heidelberg 2010

Authors and Affiliations

  • Xuping Wang
    • 1
  • Yan Shi
    • 1
  • Junhu Ruan
    • 1
  • Hongyan Shang
    • 2
  1. 1.Dalian University of TechnologyDalianChina
  2. 2.Huachiew Chalermprakiet UniversityBnagkokThailand

Personalised recommendations