The pattern of grey fuzzy forecasting with feedback

The study on forecasting method has an important meaning for both theory investigation and practical application. Based on the theories of grey system and fuzzy recognition, the pattern of multi-objective and multi-dimensional grey fuzzy forecasting with feedback is presented in this paper. At first, according to the given weights, the weighting integrated value of samples is computed. Secondly, the method of fuzzy recognition with single index is employed to calculate the fuzzy classification of the integrated value. According to the cause analysis, the fuzzy classification of the integrated value is used to compute the weights of indexes. In a similar fashion, by repeating the above processes, the weighting integrated value and fuzzy classification with given accuracy are obtained at the same time. At last, the correlation coefficient between the weighting integrated values and forecasting objects is calculated by the processes of the principle of maximal relativity, optimization of the weighting integrated value of samples, establishment of the fuzzy forecasting pattern, and checking of the model´s precision. The model is applied to predict groundwater dynamic levels, and the mean forecast accuracy of test samples is 96.50%.