طراحي مدل پيش بيني تركيبي در صنعت نفت (مدل سيستم هاي خبره تصميم گيرنده )

The Design of Combined Forecasting Model in the Oil Industry

In this research, combined forecasting is considered for managers forecasting.This model is a new approach that has been used in the past two decades and indicates considerable error reduction in forecasted results. In this study, at first, forecasting was done with some different methods that are named individual methods here. These models consist of exponential smoothing methods, trend analysis, Box-Jenkins, causal analysis and neural network model. Results of these individual forecasting methods (some selected model) are combined and compared with artificial neural network and multiple regression models. The data consists of OPEC oil demand from 1960 to 2002 as dependent variable and price, GDP, other energy demand, population, value added of industry as independent variables. Computed MSE, MAPE, indexes show considerable reduction in errors of mixed forecasting method. Finally, an expert system model is selected as preferred method, a model that has minimum error.