Sales Prediction through Neural Networks for a Small Dataset

• Rosa María Cantón Croda ^[1] ; Damián Emilio Gibaja Romero ^[1] ; Santiago Omar Caballero Morales ^[1]
  1. [1] Universidad Popular Autónoma del Estado de Puebla

     Universidad Popular Autónoma del Estado de Puebla

     México

     
• Localización: IJIMAI, ISSN-e 1989-1660, Vol. 5, Nº. 4, 2019, págs. 35-41
• Idioma: inglés
• Enlaces
  • Texto completo (pdf)
• Resumen

  • Sales forecasting allows firms to plan their production outputs, which contributes to optimizing firms' inventory management via a cost reduction. However, not all firms have the same capacity to store all the necessary information through time. So, time-series with a short length are common within industries, and problems arise due to small time series does not fully capture sales' behavior. In this paper, we show the applicability of neural networks in a case where a company reports a short time-series given the changes in its warehouse structure.

    Given the neural networks independence form statistical assumptions, we use a multilayer-perceptron to get the sales forecasting of this enterprise. We find that learning rates variations do not significantly increase the computing time, and the validation fails with an error minor to five percent.