面向大批量定制的基于改进的LS-SVM服装需求预测模型

为提高服装需求预测精度，充分考虑了服装需求量随季节、气候条件、价格、性别等因素的影响而动态变化的情况，运用模糊理论对相关影响因素进行模糊化处理后，再将这些影响因素作为服装需求量预测函数的输入变量；然后建立了以改进的二乘支持向量机(LS-SVM)方法为主、多方法融合为辅的预测模型，对服装销售量进行动态预测。实际算例验证了这一智能预测模型具有良好的精确性。

Forecasting model for apparel demand based on improved least squares support vector machine (LS-SVM) oriented to mass customization

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.