Improved GM(1, 1) model based on concave sequences and its applications

Abstract

Purpose The purpose of this paper is to improve the GM(1, 1) model based on concave sequences. Design/methodology/approach First, the restored sequence of the GM(1, 1) model is proved to be convex, and the residual characters of the GM(1, 1) model for concave sequences are analyzed. Second, two symmetry transformations are introduced to transform an original concave sequence into a convex sequence, and then the GM(1, 1) model is established based on the convex sequence. Findings Compared with the traditional modeling method, the new method has high accuracy and is applicable for all concave sequence modeling. Practical implications Two cases are used to illustrate the superiority of this modeling method. Case A is to predict China’s per capita natural gas consumption, and case B is to predict the annual output of an oilfield. Originality/value The application scope of GM (1, 1) model is greatly extended.