أستخدام نماذج السلاسل الزمنية الهجينة وغير الهجينة للتنبؤ بإعداد المسافرين لمطار بغداد الدولي

Abstract

Prediction in time series is one of the most important topics in statistical procedures and all vital areas it can help managements in the economic and strategic planning and decision-making . This research use time series hybrid models generated from the integration of Box- Jenkins (ARIMA) model  and multi-layered neural networks as The first hybrid model (ARIMA-ANN) and second (ANN-ARIMA) model and assuming series includes two components linear and non-linear with the single models such as Box- Jenkins model in which time series is a linear combination , and multi-layered neural networks in which time series has a nonlinear combination to predict the number of passengers in International Baghdad Airport , when comparing these models through a number of statistical criteria ,they show that the hybrid model (ANN-ARIMA) is the superior model because it has lower values ​​of these criteria , and it has been used to calculate the prediction of passenger numbers  for the time period from September 2015 until December 2016 , where the data were analyzed and the results were obtained based on the statistical programs package (Minitab 16 , SPSS 19) .