Nonlinear Grey Forecasting Models

Nonlinear grey forecasting models, aimed at describing more complex systems, have broader applicability than linear models, having attracted considerable attention in the grey forecasting community. Up to now, most research has focused on improving the classical models and developing novel forms, which enrich nonlinear grey forecasting model families. The existing different model forms of nonlinear grey forecasting models make it difficult for researchers to perform property analysis. Hence it is required to develop a unified methodological framework, fully illustrating the modelling paradigm. Therefore, in this section, we propose a methodological framework that subsumes various nonlinear grey forecasting models as special cases, providing a Cusum series-orientated modelling paradigm. Furthermore, by introducing an integral operator, the unified model is reduced to an equivalent integro-differential equation which provides a direct modelling paradigm.