Incorporating Feature Selection Method into Neural Network Techniques in Sales Forecasting of Computer Products

  • Chi-Jie Lu
  • Jui-Yu Wu
  • Tian-Shyug Lee
  • Chia-Mei Lian
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6677)


Sales forecasting of computer products is regarded as an important but difficult task since computer products are characterized by product variety, rapid specification changes and rapid price declines. Artificial neural networks (ANNs) have been found to be useful techniques for sales forecasting. However the inability to identify important forecasting variables is one of the main shortcomings of ANNs. For selecting an appropriate number of forecasting variables which can best improve the performance of the neural network prediction model, a commonly discussed data mining technique, multivariate adaptive regression and splines (MARS), is adapted in this study. The proposed model, firstly, uses the MARS to select important forecasting variables. The obtained significant variables are then served as the inputs for two neural network models-support vector regression (SVR) and cerebellar model articulation controller neural network (CMACNN). A real sales data collected from a Taiwanese computer dealer is used as an illustrative example. Experimental results showed that the obtained important variables from MARS can improve the forecasting performance of the SVR and CMACNN models. The proposed two-stage forecasting models provide good alternatives for sales forecasting of computer products.


Sales forecasting computer product feature selection multivariate adaptive regression splines artificial neural networks 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Thomassey, S., Fiordaliso, A.: A hybrid sales forecasting system based on clustering and decision trees. Decision Support Systems 42(1), 408–421 (2006)CrossRefGoogle Scholar
  2. 2.
    Thomassey, S., Happiette, M.: A neural clustering and classification system for sales forecasting of new apparel items. Applied Soft Computing 7(4), 1177–1187 (2007)CrossRefGoogle Scholar
  3. 3.
    Ni, Y., Fan, F.: A two-stage dynamic sales forecasting model for the fashion retail. Expert Systems with Applications 38(3), 1529–1536 (2011)CrossRefGoogle Scholar
  4. 4.
    Chang, P.C., Lai, C.Y., Lai, K.R.: A hybrid system by evolving case-based reasoning with genetic algorithm in wholesaler’s returning book forecasting. Decision Support Systems 42(3), 1715–1729 (2006)CrossRefGoogle Scholar
  5. 5.
    Chang, P.C., Liu, C.H., Wang, Y.W.: A hybrid model by clustering and evolving fuzzy rules for sales decision supports in printed circuit board industry. Decision Support Systems 42(3), 1254–1269 (2006)CrossRefGoogle Scholar
  6. 6.
    Lu, C.J., Wang, Y.W.: Combining independent component analysis and growing hierarchical self-organizing maps with support vector regression in product demand forecasting. International Journal of Production Economics 128(2), 603–613 (2010)CrossRefGoogle Scholar
  7. 7.
    Fildes, R., Nikolopoulos, K., Crone, S.F., Syntetos, A.A.: Forecasting and operational research: A review. Journal of the Operational Research Society 59(9), 1150–1172 (2008)CrossRefzbMATHGoogle Scholar
  8. 8.
    Vapnik, V.N.: The Nature of Statistical Learning Theory. Springer, New York (2000)CrossRefzbMATHGoogle Scholar
  9. 9.
    Lu, C.J., Wu, J.Y.: Forecasting financial time series via an efficient CMAC neural network. Lecture Notes in Electrical Engineering 67, 73–82 (2010)CrossRefGoogle Scholar
  10. 10.
    Friedman, J.H.: Multivariate adaptive regression splines (with discussion). The Annals of Statistics 19, 1–141 (1991)CrossRefzbMATHGoogle Scholar
  11. 11.
    Lee, T.S., Chiu, C.C., Chou, Y.C., Lu, C.J.: Mining the customer credit using classification and regression tree and multivariate adaptive regression splines. Computational Statistics and Data Analysis 50(4), 1113–1130 (2006)CrossRefzbMATHGoogle Scholar
  12. 12.
    Lu, C.J., Lee, T.S., Chiu, C.C.: Financial time series forecasting using independent component analysis and support vector regression. Decision Support Systems 47, 115–125 (2009)CrossRefGoogle Scholar
  13. 13.
    Cherkassky, V., Ma, Y.: Practical selection of SVM parameters and noise estimation for SVM regression. Neural Networks 17, 113–126 (2004)CrossRefzbMATHGoogle Scholar
  14. 14.
    Wu, J.Y., Lu, C.J.: Applying classification problems via a data mining approach based on a cerebellar model articulation controller. In: 1st Asian Conference on Intelligent Information and Database Systems, Dong Hoi City, Vietnam, pp. 61–66 (2009)Google Scholar
  15. 15.
    Wood, S.: Float Analysis: Powerful Technical Indicators using Price and Volume. John Wiley & Sons, New York (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Chi-Jie Lu
    • 1
  • Jui-Yu Wu
    • 2
  • Tian-Shyug Lee
    • 3
  • Chia-Mei Lian
    • 4
  1. 1.Department of Industrial Engineering and ManagementChing Yun UniversityTaoyuanTaiwan, R.O.C.
  2. 2.Department of Business AdministrationLunghwa University of Science and TechnologyTaoyuanTaiwan, R.O.C.
  3. 3.Department of Business and AdministrationFu Jen Catholic UniversityTaipeiTaiwan, R.O.C.
  4. 4.Graduate School of Business AdministrationFu Jen Catholic UniversityTaipeiTaiwan, R.O.C.

Personalised recommendations