Advertisement

Artificial Neural Networks for Bottled Water Demand Forecasting: A Small Business Case Study

  • Israel D. Herrera-GrandaEmail author
  • Joselyn A. Chicaiza-Ipiales
  • Erick P. Herrera-Granda
  • Leandro L. Lorente-Leyva
  • Jorge A. Caraguay-Procel
  • Iván D. García-Santillán
  • Diego H. Peluffo-Ordóñez
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11507)

Abstract

This paper shows a neural networks-based demand forecasting model designed for a small manufacturer of bottled water in Ecuador, which currently doesn’t have adequate demand forecast methodologies, causing problems of customer orders non-compliance, inventory excess and economic losses. However, by working with accurate predictions, the manufacturer will have an anticipated vision of future needs in order to satisfy the demand for manufactured products, in other words, to guarantee on time and reasonable use of the resources. To solve the problems that this small manufacturer has to face a historic demand data acquisition process was done through the last 36 months costumer order records. In the construction of the historical time series, that was analyzed, demand dates and volumes were established as input variables. Then the design of forecast models was done, based on classical methods and multi-layer neural networks, which were evaluated by means of quantitative error indicators. The application of these methods was done through the R programming language. After this, a stage of training and improvement of the network is included, it was evaluated against the results of the classic forecasting methods, and the next 12 months were predicted by means of the best obtained model. Finally, the feasibility of the use of neural networks in the forecast of demand for purified water bottles, is demonstrated.

Keywords

Long-term demand forecasting Small business Artificial neural networks 

Notes

Acknowledgments

The authors acknowledge to the research project “Optimización de la Distribución Física y en Planta en la Cadena de Suministro aplicando Técnicas Heurísticas” supported by Agreement HCD Nro. UTN-FICA-2019-0149 by Facultad de Ingeniería en Ciencias Aplicadas from Universidad Técnica del Norte. As well, authors thank the valuable support given by the SDAS Research Group (https://www.sdas-group.com).

References

  1. 1.
    Aburto, L., Weber, R.: A sequential hybrid forecasting system for demand prediction. In: Perner, P. (ed.) MLDM 2007. LNCS (LNAI), vol. 4571, pp. 518–532. Springer, Heidelberg (2007).  https://doi.org/10.1007/978-3-540-73499-4_39CrossRefGoogle Scholar
  2. 2.
    Saha, C., Lam, S.S., Boldrin, W.: Demand forecasting for server manufacturing using neural networks. In: Proceedings of the 2014 Industrial and Systems Engineering Research Conference. State University of New York at Binghamton (2015)Google Scholar
  3. 3.
    Slimani, I., El Farissi, I., Achchab, S.: Artificial neural networks for demand forecasting: application using Moroccan supermarket data. In: International Conference on Intelligent Systems Design and Applications, ISDA, June 2016, pp. 266–271 (2016).  https://doi.org/10.1109/isda.2015.7489236
  4. 4.
    Abraham, E.R., dos Reis, J.G.M., Colossetti, A.P., de Souza, A.E., Toloi, R.C.: Neural network system to forecast the soybean exportation on Brazilian port of Santos. In: Lödding, H., Riedel, R., Thoben, K.-D., von Cieminski, G., Kiritsis, D. (eds.) APMS 2017. IAICT, vol. 514, pp. 83–90. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-66926-7_10CrossRefGoogle Scholar
  5. 5.
    Fu, W., Chien, C.-F., Lin, Z.-H.: A hybrid forecasting framework with neural network and time-series method for intermittent demand in semiconductor supply chain. In: Moon, I., Lee, G.M., Park, J., Kiritsis, D., von Cieminski, G. (eds.) APMS 2018. IAICT, vol. 536, pp. 65–72. Springer, Cham (2018).  https://doi.org/10.1007/978-3-319-99707-0_9CrossRefGoogle Scholar
  6. 6.
    Hyndman, R., Athnasopoulos, G.: Forecasting: Principles and Practice. OTexts, Australia (2018)Google Scholar
  7. 7.
    Hu, Y., Sun, S., Wen, J.: Agricultural machinery spare parts demand forecast based on BP neural network. In: Applied Mechanics and Materials, pp. 1822–1825 (2014)Google Scholar
  8. 8.
    Matich, D.: Redes Neuronales: Conceptos Básicos y Aplicaciones, Rosario (2001)Google Scholar
  9. 9.
    Ramasubramanian, K., Singh, A.: Machine Learning Using R. Apress, Berkeley (2019)CrossRefGoogle Scholar
  10. 10.
    Scenio: ¿Qué es una Red Neuronal? Parte 2 : La Red | DotCSV, (2018)Google Scholar
  11. 11.
    Crone, S.F., Kourentzes, N.: Feature selection for time series prediction – a combined filter and wrapper approach for neural networks. Neurocomputing 73, 1923–1936 (2010).  https://doi.org/10.1016/j.neucom.2010.01.017CrossRefGoogle Scholar
  12. 12.
    Hanke, J.: Pronósticos en los negocios, México (2010)Google Scholar
  13. 13.
    Chopra, S., Meindl, P.: Supply Chain Management: Strategy, Planning, and Operation (2013)Google Scholar
  14. 14.
    Heizer, J., Render, B., Munson, C.: Operations management (2016)Google Scholar
  15. 15.
    Montemayor, E.: Métodos de pronósticos para negocios, Mexico (2013)Google Scholar
  16. 16.
    Hanke, J., Wichern, D.: Business forecast. Pearson Educación (2010)Google Scholar
  17. 17.
    Business Forecast Systems, Inc.: Better decisions demand forecast accuracy - forecast pro. https://www.forecastpro.com/

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Israel D. Herrera-Granda
    • 1
    Email author
  • Joselyn A. Chicaiza-Ipiales
    • 1
  • Erick P. Herrera-Granda
    • 1
  • Leandro L. Lorente-Leyva
    • 1
  • Jorge A. Caraguay-Procel
    • 1
  • Iván D. García-Santillán
    • 1
  • Diego H. Peluffo-Ordóñez
    • 2
  1. 1.Facultad de Ingeniería en Ciencias AplicadasUniversidad Técnica del NorteIbarraEcuador
  2. 2.Escuela de Ciencias Matemáticas y Tecnología InformáticaYachay TechSan Miguel de UrcuquíEcuador

Personalised recommendations