Evaluating Prediction Models for Airport Passenger Throughput Using a Hybrid Method

Abstract

This paper proposes a hybrid evaluation method to assess the prediction models for airport passenger throughput (APT). By analyzing two hundred three airports in China, five types of models are evaluated to study the applicability to different airports with various airport passenger throughput and developing conditions. The models were fitted using the historical data before 2014 and were verified by using the data from 2015–2019. The evaluating results show that the models employed for evaluating perform well in general except that there are insufficient historical data for modelling, or the APT of the airports changes abruptly owing to expansion, relocation or other kinds of external forces such as earthquakes. The more the APT of an airport is, the more suitable the models are for the airport. Particularly, there is no direct relation between the complexity and the predicting accuracy of the models. If the parameters of the models are properly set, time series models, causal models, market share methods and analogy-based methods can be utilized to predict the APT of 88% of studied airports effectively.

Medium- and Long-Term Prediction of Airport Carbon Emissions under Uncertain Conditions Based on the LEAP Model

“…It is assumed that within the predicted period, CAN continues to have a saturated capacity, and there is no substantial improvement in airspace conditions. Socioeconomic factors play a decisive role in airport throughput, and previous studies usually predicted airport throughput based on socioeconomic factors [35][36][37]. Since the epidemic will have a lasting impact on airport development, the airport throughput prediction based on socioeconomic factors will no longer be accurate and needs to be further revised according to the impact of the epidemic.…”

“…), gross value of secondary industry ( 5x ), gross value of tertiary industry ( 6x ), tourism income ( 7x ), and retail sales of social consumer goods ( 8x ) [35][36][37]. In order to identify the key socioeconomic factors affecting airport throughput, this study used the feature importance measurement method based on random forest to rank the influencing factors.…”

“…As shown in Figure 6, the neural network model used in this study has a structure of 4 × 3 × 2, with 4 input layers, 3 hidden layers, and 2 output layers. The input layer consists of the four key factors of airport throughput, and the output layer is the airport passenger Socioeconomic factors play a decisive role in airport throughput, and previous studies usually predicted airport throughput based on socioeconomic factors [35][36][37]. Since the epidemic will have a lasting impact on airport development, the airport throughput prediction based on socioeconomic factors will no longer be accurate and needs to be further revised according to the impact of the epidemic.…”

“…It is generally acknowledged that airport throughput is related to factors such as GDP (x 1 ), resident population (x 2 ), urbanization rate (x 3 ), gross value of primary industry (x 4 ), gross value of secondary industry (x 5 ), gross value of tertiary industry (x 6 ), tourism income (x 7 ), and retail sales of social consumer goods (x 8 ) [35][36][37]. In order to identify the key socioeconomic factors affecting airport throughput, this study used the feature importance measurement method based on random forest to rank the influencing factors.…”

Energy Forecasting Model for Ground Movement Operation in Green Airport

“…Ref. [30] evaluates the accuracy of prediction models for airport passenger throughput using a hybrid approach. The main objective of this study is to identify the most effective model for predicting airport passenger traffic, which holds significant importance for airport management and planning.…”