TIME SERIES FORECASTING MODELS OF NON-SCHEDULED PASSENGER AIR TRANSPORTATION

Abstract

The change in the time series of non-scheduled passenger air transportation is random and variable, which creates a number of problems in forecasting the demand for this type of transportation. In calculations based on trend models, it is usually not possible to take into account all extraneous factors affecting non-scheduled passenger air transportation. For this reason, the accuracy and practical significance of the forecast are low. Considering the mentioned facts, this paper investigates the application of combined autoregressive integrated moving average (ARIMA) and support vector machine (SVM) methods to improve the accuracy of charter air transportation demand forecasting. ARIMA and SVM models usually complement each other in forecasting due to their inherent characteristics. These features include detecting temporal dependencies and trends, as well as handling non-linear relationships within historical data. The integration of these methods aims to obtain optimal forecast results using the time series analysis of the ARIMA model and the non-linear relationship detection feature of the SVM model. The obtained results emphasize the ability of ARIMA-SVM models to adapt to the dynamic demand patterns of non-scheduled air transportation and also offer a number of efficient ideas for the optimization of operational strategies and resource allocation in this field. The theoretical-practical results of this study, conducted with ARIMA and SVM methods, will be effective in the field of non-scheduled passenger air transportation.