Scholarly record

SEASONAL FORECASTING FOR AIR PASSENGER TRAFIC

K. Chudy-Laskowska, T. Pisula

Abstract

Air transport is currently one of the fastest-growing service sectors. People constantly travel for various reasons (tourism, business) to distant locations worldwide. Consequently, analyses of data concerning both passenger and cargo air traffic is of great importance in designing development strategies for regions with airports in their resources. The main purpose of this study is to prepare a forecast of air passenger transport in the one of the airport which is located in south-western of Poland. There are very few publications regarding passengers traffic forecast in Podkarpacie Region. This is a very important topic for the region development, and therefore it has been taken in this study. The research period covers the period from January 2007 to October 2016. Data were presented in monthly cycles. Four research methods were used for forecast calculations: seasonal exponential smoothing, seasonal ARIMA, artificial neural networks and support vector machines (SVM). The Kruskal - Wallis analysis of variance (ANOVA) was used to ascertain if there were any statistically significant differences in mean passenger volumes in individual months. A confidence level of ?=0.05 was assumed for the test. The final value of forecast volumes was determined by employing the results of all methods discussed in the article. The forecast retains the characteristics of historical data, i.e. seasonal fluctuations, though its values do not rise substantially. Rather, it seems that the dynamic growth is slowing down. The passenger traffic is linked to many factors, and the inclusion of the time factor alone is a considerable simplification. It is a well-known fact that air passenger transport may be affected by many diverse variables (the future amount of the GDP, the population of the country, the volume and value of foreign exchange, consumption levels). To a certain extent such forecasts enable the right decisions on future activities in the analysed area to be taken. Thanks to the use of suitable forecasting methods, key decisions become more justified and substantiated with an appropriate analysis.

Publication Impact Profile

No metrics available.

PLUMX see details

DOI resolver: doi.org/10.5593/sgemsocial2017/14/S04.089

Publication details

Back to publication list