application of genetic algorithm in inflation forecasts combination

inflation forecasting has been one of the requirements for the implementation of monetary policy in countries which their monetary authorities are pursuing inflation targeting regime. however, owing to central bank independence in one hand and as well as the lagged effects of monetary policies on inflation in the other, the monetary authorities should have the sound perspective about the future inflation, regarding the control of economy in the line of predetermined objectives. in this way, due to the limitations of single model, different forecasting models have frequently been used in different empirical studies to produce better forecast comparing to individual forecasting model. moreover, it is found that simple combinations that ignore correlations between forecast errors often dominate more refined combination schemes. in this article we apply the genetic algorithm heuristic approach to find the optimal combination weights for inflation forecasts. jel classification: c13، c53، e37