Study on parameters characteristics of NGM (1,1,k) prediction model with multiplication transformation

Abstract

Purpose -The purpose of this paper is to study the properties of the NGM (1,1,k) prediction model with multiplication transformation and reduce its modeling complexity. Design/methodology/approach -The authors improved this model by putting forward a formula to solve its parameters, building an algorithm for optimizing the NGM (1,1,k) model in terms of the least modeling error and designing a key technology for the implementation of this algorithm. The optimized NGM (1,1,k) model is built accordingly. The parameter characteristics of the two models under multiple transformations and its effect of the simulation value and forecasting value are analyzed by studying the properties of multiple transformation of the two models. Findings -The research finding shows that the modeling accuracies of the NGM (1,1,k) model and the optimized NGM (1,1,k) model are all in no relation to multiple transformations. Practical implications -The above results imply that the data level can be reduced; the process of building the NGM (1,1,k) model and the optimized NGM (1,1,k) model can be simplified; but the simulative and predictive accuracy of the two models remain unchanged. Originality/value -The paper succeeds in realising the properties of NGM (1,1,k) model and the optimized NGM (1,1,k) model by using the method of multiplication transformation, which is helpful for understanding the modeling mechanism and expanding the application range of the NGM (1,1,k) model.

Forecasting the diffusion of ISO/IEC 27001: a Grey model approach

“…, 2001); on optimizing the parameters of the models (e.g. Jie and Bo, 2012); on strategies aimed at improving the initial values included in the models (e.g. Dang et al.…”

“…Ji et al, 2001); on optimizing the parameters of the models (e.g. Jie and Bo, 2012); on strategies aimed at improving the initial values included in the models (e.g. Dang et al, 2005); and on identifying the application boundaries of the different models (e.g.…”

Soil organic matter content GM(0,N) estimation model based on hyper‐spectral technique

“…But when the original data sequence is of high growth or the sequence data changes rapidly, the GM(1,1) model's prediction accuracy will be low (Liu and Forrest, 1997). Therefore, in the past 30 years, many scholars have discussed the GM(1,1) model's nature (Li, 1998), application region (Li and Deng, 1999), establishing model conditions (Tang, 2000), model optimization, model expansion and so on; they have achieved fruitful research results (Li, 2004;Xiao and Peng, 2011;Cui and Zeng, 2012), and now they are still improving and developing the grey GM(1,1) model (Wei and Liu, 2011) and grey GM(0,N) model (Wu et al, 2009;Chen et al, 2013). Author proposes the grey relationship recognition prediction model of the SOM content hyper-spectral inversion under the uncertainties of the SOM content hyper-spectral inversion (Li et al, 2011).…”

GM(1, 1) forecast under function cot x transformation

“…For applications in the real world, the fitting accuracy of GM(1, 1) is an important technical foundation of determining the forecasting results reasonable or not. In terms of GM(1, 1) itself, experts and scholars studied on the following fields: initial values' selection (Dang et al, 2005;Zhang and Hu, 2001), the model parameter optimization (Xiao, 2000;Cui and Zeng, 2012;He et al, 2005), and the structure of background values (Tan, 2005;Li and Dai, 2004). All of these improve the fitting accuracy of model and obtain some significant results.…”