Long term sales forecasting for industrial supply chain management

One the most important components of supply chains is sales forecasting. The problem of sales forecasting considered in this paper raises a number of requirements that must be observed in order for the long-term planning of the supply chain to be realized successfully. These include long forecasting horizons (up to 52 periods ahead), a high number of quantities to be forecasted, which limits the possibility of human intervention, and frequent introduction of new articles (for which no past sales are available for parameter calibration) and withdrawal of running articles. The problem has been tackled by use of the Holt-Winters method and by use of Feedforward Multilayer Neural Networks (FMNN) applied to sales data from two German companies.