一类准指数序列的模型优化

Optimization for a Kind of Quasi-index Sequence Model

在传统GM(1,1)模型基础上,结合最小二乘法原理提出:对本身已具有准指数规律的原始序列直接进行建模,并在此基础上对新模型背景值进行适当优化.克服传统GM(1,1)模型建模过程中的盲目性,并提高了拟合与预测精度.

Basing on the traditional GM（1,1）model and combining the least square method principle, this article present a improved method which directly builds a model with quasi- index rule original sequence, and a suitable optimization in background value of the new model is also mentioned. The present method can overcome the blindness character of the tradition GM（1,1） model, and it can inevitably enhance the accuracy of fitting and prediction.