Performance Evaluation of ARIMA and SARIMA Models for Modeling and Forecasting Passenger Numbers at Misurata International Airport (2021–2025)

Abstract

This study compares the performance of ARIMA and SARIMA models in modeling and forecasting the number of air passengers at Misrata International Airport, using monthly time-series data covering the period from 2021 to 2025. The study adopts the Box–Jenkins methodology to construct and compare several models, including ARIMA(1,1,1), SARIMA(1,1,1)(0,0,1), and SARIMA(1,1,1)(0,1,0). The models were evaluated and compared using several statistical criteria and forecasting accuracy measures, including Mean Absolute Error (MAE), Root Mean Square Error (RMSE), the Coefficient of Determination (R²), and the Akaike Information Criterion (AIC). The results demonstrate that the seasonal SARIMA models outperform the ARIMA model in capturing the seasonal patterns of the time series and improving forecasting accuracy. The SARIMA(1,1,1)(0,1,0) model achieved the highest coefficient of determination     R² = (0.9535) and the lowest values of RMSE (511.28) and MAE (415.047). In contrast, the SARIMA(1,1,1)(0,0,1) model achieved the lowest AIC value AIC = (19.2539). Based on the forecasting accuracy measures, the SARIMA(1,1,1)(0,1,0) model was found to be the most suitable model for representing the seasonal behavior of passenger numbers at Misrata International Airport. These findings indicate that incorporating a seasonal component into time-series models can enhance modeling efficiency and improve the accuracy of passenger traffic forecasts