Study on grey prediction model GM(1,1)and its application based on amplitude compression transformation

Abstract

With respect to the issue that traditional grey model GM(1,1) hardly satisfies the prediction requirement of sequence fluctuation, a new data processing method of dealing with amplitude compression transformation and average weighted transformation is proposed. Furthermore, the fact that amplitude compression transformation is able to decrease the fluctuation of sequences and average weighted transformation can enhance the smoothness of sequences proved theoretically. Grey prediction model GM(1,1) is established based on applying amplitude compression transformation and average weighted transformation to exchange the fluctuation sequences. Finally, an application to forecast China's extraordinarily serious road traffic accidents is presented to illustrate the proposed framework.