THE APPLICATION OF COMBINATION MODEL ON SHORT-TERM PRICE FORECASTING OF AGRICULTURE PRODUCTS---THE EMPIRICAL ANALYSIS OF APPLE PRICE
WANG Chuan1, ZHAO Junye1, ZHAO Yousen2
Author information+
1.Agricultural Information Institute of Chinese Academy of Agricultural Science, Beijing 100081; 2.Information Center of Beijing Municipal Bureau of Agricultural, Beijing 100029
Taking the apple price of wholesale market in China as study object, using the data of 300 weeks from 2006-7-7 to 2012-3-30 as analysis sample, by statistic test of the data characteristics such as Smooth, Trend, Seasonality, Heteroskedasticity etc. of time series, we choose the Double exponential smoothing model, the multiplicative model of Holt-Winters, ARIMA (1,1,4) model as applicable model of short term forecast of apple market price in China. Based on these results, we establish the Combination Forecasting Model with the least sum of error square as optimal criteria. By carrying out the forecast of apple market price in future three periods, the results show that the accuracy of combination forecasting is higher than individual time series model, and the combined forecasting method is fully applicable to the short-term forecasts of agricultural products market price.
WANG Chuan, ZHAO Junye, ZHAO Yousen.
THE APPLICATION OF COMBINATION MODEL ON SHORT-TERM PRICE FORECASTING OF AGRICULTURE PRODUCTS---THE EMPIRICAL ANALYSIS OF APPLE PRICE. Journal of Systems Science and Mathematical Sciences, 2013, 33(1): 89-96 https://doi.org/10.12341/jssms12022