Forecast the Erbil International Airport Data Using Statistical Methods

Abstract:

This paper concentrates to use two advanced statistical methods (Box–Jenkins and Adaline Neural Network) to forecast future values using data from the past values of a variable of all people that they had taken Erbil Airport as a way to move to other countries. The real data set were collected and obtained from Erbil International Airport and The sample observation consisted of (72) month, from the Airport transfer process during a certain time period 2017-2022. For the purpose of choosing the best model fit for these two models, the values of three criteria measures Mean Square Error (MSE), Mean Absolute Deviation (MAD) and Akaike Information Criterion (AIC) have been obtained from the estimated models. Additionally, the results showed that although the parameter estimations of the two models are not directly comparable, the results of all two models are not similar. Software packages StataV.16, SPSS V.26 and Matlab (R2013a) were used to fit the models. 

Keywords: Artificial Neural Network, Adaline Neural Network, Box-Jenkins methodology, ARIMA models