, Volume 14, Issue 3, pp 309–325 | Cite as

An application of support vector machines to sales forecasting under promotions

  • G. Di PilloEmail author
  • V. Latorre
  • S. Lucidi
  • E. Procacci


This paper deals with sales forecasting of a given commodity in a retail store of large distribution. For many years statistical methods such as ARIMA and Exponential Smoothing have been used to this aim. However the statistical methods could fail if high irregularity of sales are present, as happens for instance in case of promotions, because they are not well suited to model the nonlinear behaviors of the sales process. In recent years new methods based on machine learning are being employed for forecasting applications. A preliminary investigation indicates that methods based on the support vector machine (SVM) are more promising than other machine learning methods for the case considered. The paper assesses the application of SVM to sales forecasting under promotion impacts, compares SVM with other statistical methods, and tackles two real case studies.


Machine learning Support vector machines Sales forecasting Promotion policies Nonlinear optimization 

Mathematics Subject Classification

62M20 68T05 90B05 90B60 90C30 


Compliance with ethical standards

We confirm that this submission complies with all ethical standards of 4OR. In particular we confirm that this work has been partially funded by ACT-OperatiosResearch SRL, contract 602/2010 on “Forecasting by Neural Networks and SVM”.

Author contribution

All authors of this paper have directly participated in the planning, execution, or analysis of this study. All authors of this paper have read and approved the final version submitted. The contents of this manuscript have not been copyrighted or published previously. The contents of this manuscript are not now under consideration for publication else- where; The contents of this manuscript will not be copyrighted, submitted, or published else- where, while acceptance by the Journal is under consideration; Department representative is fully aware of this submission.


  1. Alon I, Qi M, Sadowski RJ (2001) Forecasting aggregate retail sales: a comparison of artificial neural networks and traditional methods. J Retail Consum Serv 8:147–156CrossRefGoogle Scholar
  2. Ansuj AP, Camargo ME, Radharamanan R, Petry DG (1996) Sales forecasting using time series and neural networks. Comput Ind Eng 31:421–424CrossRefGoogle Scholar
  3. Bo C, Lu A, Wang Z, Zhang S (2006) Study and application on dynamic modeling method based on SVM and sliding time window techniques. In: Proceedings of the 6th world congress on intelligent control and automation. IEEE, pp 4714–4718Google Scholar
  4. Burges CJC (1998) A tutorial on support vector machines for pattern recognition. Data Min Knowl Discov 2:121–167CrossRefGoogle Scholar
  5. Chang CC, Lin CJ (2014) LIBSVM: a library for support vector machines.
  6. Chang PC, Liu CH, Fan CY (2009) Data clustering and fuzzy neural network for sales forecasting: a case study in printed circuit board industry. Knowl Based Syst 22:344–355CrossRefGoogle Scholar
  7. Cristianini N, Shawe-Taylor J (2000) An introduction to support vector machines and other kernel-based learning methods. Cambridge University Press, CambridgeCrossRefGoogle Scholar
  8. Crone SF, Preßmar DB (2006) An extended evaluation framework for neural network publications in sales forecasting. In: Proceedings of the international conference on applied artificial intelligence AIA’06. ACTA Press, pp 179–186Google Scholar
  9. Cui D, Curry D (2005) Prediction in marketing using the support vector machine. Mark Sci 24:595–615CrossRefGoogle Scholar
  10. Das P, Chaundhury S (2007) Prediction of retail sales of footwear using feedforward and recurrent neural networks. Neural Comput Appl 16:491–502CrossRefGoogle Scholar
  11. Di Pillo G, Latorre V, Lucidi S, Procacci E (2013) An application of learning machines to sales forecasting under promotions, Tech. Rep. Department of Computer Control and Management Engineering, Sapienza University of Rome, n. 4.
  12. Gür Ali Ö, Sayin S, van Woensel T, Fransoo J (2009) SKU demand forecasting in the presence of promotions. Expert Syst Appl 36:12340–12348CrossRefGoogle Scholar
  13. Kuo RJ, Hu TL, Chen ZY (2009) Application of radial basis function neural network for sales forecasting. In: Proceedings international Asia conference on informatics in control, automation and robotics. IEEE, pp 325–328Google Scholar
  14. Kuo RJ, Xue KC (1998) A decision support system for sales forecasting through fuzzy neural networks with assymetric fuzzy weights. Decis Support Syst 24:105–126CrossRefGoogle Scholar
  15. Levis AA, Papageorgiou LG (2005) Customer demand forecasting via support vector regression analysis. Chem Eng Res Des 83:1009–1018CrossRefGoogle Scholar
  16. Makridakis S, Wheelwright SC, Hyndman RJ (1998) Forecasting: methods and applications. Wiley, New YorkGoogle Scholar
  17. Thiesing FM, Middelberg U, Vornberger O (1995) Short term prediction of sales in supermarkets. In: Proceedings of the international conference on neural networks. IEEE, pp 1028–1031Google Scholar
  18. Thiesing FM, Vornberger O (1997) Sales forecasting using neural networks. In: Proceedings of the international conference on neural networks. IEEE, pp 2125–2128Google Scholar
  19. Trapero JR, Kourentzes N, Fildes R (2015) On the identification of sales forecasting models in the presence of promotions. J Oper Res Soc 66:299–307CrossRefGoogle Scholar
  20. West PM, Brockett PL, Golden LL (1997) A comparative analysis of neural networks and statistical methods for predicting consumer choice. Mark Sci 16:370–391CrossRefGoogle Scholar
  21. Wu Q, Yan HS, Yang HB (2008) A forecasting model based on support vector machine and particle swarm optimization. In: Proceedings of the workshop on power electronics and intelligent transportation systems. IEEE, pp 218–222Google Scholar
  22. Zhang G, Patuwo BE, Hu MY (1997) Forecasting with artificial neural networks: the state of the art. Int J Forecast 14:35–62CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2016

Authors and Affiliations

  • G. Di Pillo
    • 1
    Email author
  • V. Latorre
    • 1
  • S. Lucidi
    • 1
  • E. Procacci
    • 2
  1. 1.Department of Computer Control and Management EngineeringSapienza University of RomeRomeItaly
  2. 2.ACT-OperationsResearch SRLRomeItaly

Personalised recommendations