An application of genetic programming to economic forecasting

In this paper, we propose an application of genetic programming to economic forecasting that can obviously improve traditional economic forecasting methods; the latter can only obtain rough fitting curves with unsatisfactory results. Forecasted and estimated standard errors are also computed and analyzed. Using practical historical data from Statistical Yearbooks of the People's Republic of China in recent years, an automatically generated mathematical model of economic forecasting by genetic programming is established. Forecasting results indicate that the accuracy obtained by genetic programming is obviously higher than traditional methods such as linear, exponential, and parabolic regression methods.