摘要
由于常州市的GDP数据序列分布具有非齐次指数性和非凸凹一致性的特点,传统的灰色预测模型难以获得理想的效果。无偏差GM(1,1,k)模型从灰导数和背景值两个角度优化,实现了对于非齐次指数函数的无偏拟合。文中运用无偏差GM(1,1,k)预测常州市GDP,取得了较好的效果。平均预测误差为1.61965%,比GM(1,1)模型平均预测误差3.90670%降低了58.54174%;比传统GM(1,1,k)模型的平均预测误差8.67019%降低了81.13193%。由模型预测得到2018年常州市国内生产总值为7053.640亿元。
Because of the non-homogeneous exponential and non-convex concave consistency of GDP data series distribution of the city of Changzhou,the traditional grey forecasting model is difficult to be used to achieve ideal results.The unbiased GM(1,1,k)model is optimized from grey derivative and background value to realize unbiased fitting of non-homogeneous exponential function.The GM(1,1,k)has been used to predict the GDP of Changzhou,which has achieved good results.The average prediction error is 1.61965%,which is 58.54174%lower than the average prediction error of GM(1,1)model 3.90670%,and 81.13193%lower than the average prediction error of traditional GM(1,1,k)model 8.67019%.According to the prediction of the model,the gross domestic product of Changzhou in 2018 was 705 billion 364 million yuan.
作者
王艳
WANG Yan(School of Continuing Education of Wuhan University of Technology,Hubei,Wuhan 430070,China)
出处
《常州工程职业技术学院学报》
2018年第4期20-25,40,共7页
Higher Vocational Studies of Changzhou Vocational Institute of Engineering
