Title: Application of GM(1,1)-Markov chain combined model to China's automobile industry

Authors: Guo-Dong Li, Daisuke Yamaguchi, Masatake Nagai

Addresses: Graduate School of Engineering, Kanagawa University, 3–27–1 Rokkakubashi, 221–8686 Yokohama City, Japan. ' Graduate School of Engineering, Kanagawa University, 3–27–1 Rokkakubashi, 221–8686 Yokohama City, Japan. ' Graduate School of Engineering, Kanagawa University, 3–27–1 Rokkakubashi, 221–8686 Yokohama City, Japan

Abstract: In this paper, we propose a new dynamic analysis model which combines the first-order one-variable grey differential equation model (abbreviated as GM(1,1) model) from grey system theory and the Markov chain model from stochastic process theory. We abbreviate the combined GM(1,1)-Markov chain model to MGM(1,1) model. This combined model takes advantage of the high predicting power of the GM(1,1) model and at the same time takes advantage of the predicting power of Markov chain modelling on the discretised states based on the GM(1,1) modelling residual sequence. For prediction accuracy improvements, Taylor approximation is further applied to the MGM(1,1) model. We call the improved version the T-MGM(1,1) model. As an illustrative example, we use statistical data recording the number of China|s privately owned vehicles from 1986 to 2004 for a validation of the effectiveness of the T-MGM(1,1) model.

Keywords: automobile industry; prediction models; grey system theory; first-order one-variable grey differential equation model; GM(1,1) model; Markov chain; Taylor approximation method; China.

DOI: 10.1504/IJISE.2007.012466

International Journal of Industrial and Systems Engineering, 2007 Vol.2 No.3, pp.327 - 347

Published online: 16 Feb 2007 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article