Demand forecasting method for seasonal clothing based on constructed gene database

New style seasonal clothing has these features: few historical sale data and short life cycle. Therefore,it's not appropriate to forecast the demand of new style seasonal clothing using conventional forecast method based on data sequence. However,there exist lots of characteristic information in apparel enterprises' POS data. The method of hierarchical clustering and dynamic time warping( DTW) was employed to extract characteristic information from POS data in order to build a sale gene database. And a forecasting method was put forward to figure out the demand of new style seasonal clothing based on the constructed gene database,which computed the similarity between a new clothing and a gene of the characteristic database,searched the nearest gene,and computed the demand of a new style seasonal clothing based on the information from the nearest gene. The proposed method provides a solution for apparel companies to forecast its demand quantitatively based on their POS data,and can be used to build a quick response system to provide solutions. An experiment was carried out,which extracted the gene database based on 2011 POS data of a famous women apparel enterprise,and the new stock keeping units sold between 1st,March,2012 and 31th,July,2012 were used to forecast its demand based on the constructed gene database. And the result proved that the proposed forecasting method is workable.