Research On Passenger Volume Forecast Of Civil Aviation Based On Combination Model

As one of the most important industries in the national economy and social development,the civil aviation has developed rapidly in recent years,and the passenger volume of civil aviation increases steadily every year.The passenger volume of civil aviation affects the construction of airport,the procurement of aircraft,the planning and development of airlines directly.Therefore,in order to make the aviation industry play a full role in the development of China's national economy and promote the rapid and efficient development of the construction of air passenger transport,at the same time,it provides scientific basis for the management and other related work of civil aviation enterprise,the research and forecast of civil aviation transportation traffic should not be ignored.Because the single model can not fully reflect the information of passenger volume of civil aviation,this paper introduces the method of combined model to study and predict the data.In order to improve the prediction accuracy of the passenger volume of civil aviation,this paper uses the statistical software such as R,E views,SPSS and other tools,uses support vector regression machine,seasonal autoregressive sum moving average model and Winters linear exponential smoothing model to predict civil aviation passenger volume,and the average relative error and root mean square error are used to analyze each single model.Then the single model is used to extrapolate the passenger volume of January 2019 to June 2019.Then using the equal weight method,the simple weighted average method,the variance reciprocal method,the mean square error inverse method,the advantage matrix method and the combined prediction model based on the minimum error sum of squares to combine the test samples of the three single models.It is found that the average relative error and the root mean square error of each combination model are less than a single model.In order to improve the prediction accuracy of the passenger volume of civil aviation,a combination model based on IOWA operator is introduced.Because the precision of each single model is different at different times,it is not appropriate to give the same weight at different times of a single model,and the IOWA operator can sort the prediction results of a single model at the same timer to achieve the results of orderly empowerment.Through forecasting and analyzing the passenger volume of civil aviation in our country,and comparing the forecast results of each model,the combination model based on IOWA operator has high precision,reliability and practicability for the forecast of passenger volumeof civil aviation.It can play a leading role in the development of civil aviation industry in China.