The Research of Improved Grey-Markov Algorithm

Abstract

When using Grey-Markov model for prediction, the forecast curve of GM(1,1) model must pass through the point (1,x(0)(1)) is usually assumed as the known prerequisite condition before moving on to the next step. However, this kind of means is groundless, and the result we get is not necessarily the optimal solution. This paper introduces a different Grey-Markov model which is based on a kind of improved GM (1,1) algorithm and applied it to the sales forecast. The result shows that this model is working well in sales forecast. At the same time, the comparison and analysis of the prediction result of this model also helps to prove that there is no direct connection between GM(1,1) model and the first data element of the raw time series.