Forecasting of Seasonal Apparel Products

Abstract

Demand forecasting of fashion apparel products has to cope with serious difficulties in order to get more accurate forecasts early enough to influence production decisions. Demand has to be anticipated at an early date due to long production lead times. Due to the absence of historical sales data for new products, standard statistical forecasting methods, like, e.g., regression, cannot easily be applied. This contribution applies selected methods into improve forecasting customer demand of fashion or seasonal apparel products. We propose a model which uses retailer pre-orders of seasonal apparel articles before the start of their production to estimate later, additional post-orders of the same articles during the actual sales periods. This allows forecasting of total customer demand based on the pre-orders. The results show that under certain circumstances it is possible to find correlations between the pre-orders and post-orders of those articles, and thus better estimate total demand. The model contributes to the improvement of production volumes of apparel articles, and thus can help reduce article stock-outs or unwanted surpluses.