最优组合预测方法在家用汽车需求预测中的应用  

Application of an Optimal Combined Forecasting Method to Prediction of Demand for Private Cars

作　　者：赵韩[1] 许辉[1] 梁平[1] 陈传魁[1] 陈欢[1] 

机构地区：[1]合肥工业大学机械与汽车工程学院,安徽合肥230009

出　　处：《工业工程》2008年第1期126-128,133,共4页Industrial Engineering Journal

摘　　要：为了提高预测的准确性,引入了组合预测模型,将几个单一预测模型有机地结合起来,综合各个预测模型的优点,对未来几年内家用轿车需求进行预测。通过使组合预测误差平方和最小,确定各个单一预测方法的权重系数,得出更为准确的预测结果。计算结果表明该方法具有较好的实用性。This paper forecasts the demand for private cars in coming years. To improve the accuracy of forecasting, the paper presents a combined forecasting method, which integrates several single forecasting methods. Optimal weights are determined by minimizing the sum of squared errors. The combined forecasting method is rather practicable.

关 键 词：需求预测 组合预测方法 灰色系统理论 

分 类 号：N945[自然科学总论—系统科学]