Abstract:

For improving forecast accuracy of apparel demand, this paper, having given full its consideration of affecting factors such as season, climate conditions, price, gender etc. developed a forecast model mainly based on least squares support vector machine, including processing the above factors with fuzzy theory and using these factors as input variables. A forecasting model mainly based on improved least square support vector machine (LS-SVM) and other methods was constructed. Dynamic forecast of apparel demand is achieved, and practical applications show that this intelligent forecasting model has high accuracy.