Predictions Of Important Social And Economic Indicators In Shandong Province Based On Combination Prediction Method

Shandong Province is in the key period of the transformation of new and old kinetic energy and economic development.Forecasting its economic development has an important guiding significance for the formulation of a reasonable strategy,which is also a concern of the general public.As an important economic indicator,GDP has always been concerned by everyone,but the economic system is a complex comprehensive system,and only analyzing GDP is one-sided.So,in this paper,I selected several representative and common indicators from the indicators of the economic system for analysis and prediction,in order to analyze the economic development situation of Shandong Province comprehensively and put forward feasible suggestions.The single prediction model has the disadvantages of one-sided information and unstable prediction.Considering the merits and demerits of ARIMA model,GM(1,1)model and Double Exponential Smoothing method,this paper uses the combination forecasting method to forecast the economic indexes,improving prediction accuracy and reliability.Because of selecting models based on the forecasting error of single model with strong chance and easy to discard useful information,this paper proposes a single model selection method based on Grey Relational Analysis and Optimal Combination Redundancy Screening to choose single models to be combined.The weight of the model is calculated by the reciprocal method of variance and the reciprocal method of mean square error.Based on the principle of the least Sum of squares of relative errors and mean relative error,the combined forecasting model is established to predict the economic indicators of Shandong Province.On this basis,the feasible suggestions are put forward from the aspects of economic aggregate,economic growth,energy supply and people's living standards.