Abstract: Prediction models in traditional gray system involved various factors and fell short in predicting efficiency and precision. An optimized prediction model was put forward by combining the rough theory and the SVM method. The attribute deduction method was first employed on the inconsistent decision table to seek for the core attribute set, which could enable the prediction model to focus better on narrow and specific attribute fields with higher efficiency. A gray model was applied in the optimized dataset. The result parameters were then treated as the input data of a support vector machine for model prediction. China’s census data (1990～2010) were also applied in population prediction. Experimental results showed that this model had better accuracy and higher efficiency than the existing models.

Key words: attributes reduction, support vector machine, grey system, forecasting model, growth rate of population