Forecasting air passenger traffic flow based on the two-phase learning model
- PDF / 1,647,712 Bytes
- 23 Pages / 439.37 x 666.142 pts Page_size
- 60 Downloads / 175 Views
Forecasting air passenger traffic flow based on the two‑phase learning model Xinfang Wu1 · Yong Xiang2,3 · Gang Mao2,3 · Mingqian Du2,3 · Xiuqing Yang2,3 · Xinzhi Zhou1 Accepted: 2 September 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract The future airports will head toward a highly intelligent direction, like the unmanned check-in services, while the scale and resources allocation of the ground service are tightly related to the air passenger flow. Therefore, forecasting passenger flow accurately will affect the development of future airports and the optimization of service of civil airlines significantly. As a kind of time series, air passenger flow is influenced by multiple factors, particularly, the stochastic part of seasonality, trend and volatility. These will ultimately affect the accuracy of the prediction. Therefore, this paper introduces a prediction model based on a two-phase learning framework. In phase one, various predictors cope with different features of time series in parallel and the prediction results are integrated in phase two. Furthermore, this paper has compared principal error indicators with actual data and results show that the twophase learning model performs better than current fusion models and owns stable performance. Keywords Air passenger traffic flow · Two-phase learning model · Stochastic volatility · Fusion models · Forecasting method
* Xinzhi Zhou [email protected] Xinfang Wu [email protected] 1
College of Electronics and Information Engineering, Sichuan University, Chengdu, Sichuan, China
2
The Second Research Institute of CAAC, Chengdu, Sichuan, China
3
Civil Aviation Logistics Technology Company Limited, Chengdu, Sichuan, China
13
Vol.:(0123456789)
X. Wu et al.
1 Introduction With the steady growth of the global economy and the rapid development of the air transport industry in developing countries such as China and India, the world’s civil aviation passenger traffic and the amount of baggage carried by passengers are increasing day by day. According to the 2019 SITA Baggage IT Insights report [1] released by the Society International De Telecommunication Aero-nautiques (SITA), the global passenger traffic flow has surpassed 4.36 billion in 2018, with a conservative estimate of over 4 billion pieces of baggage handled at the airports. Undoubtedly, the forecasts of air traffic passenger flow are not only of great reference value for airlines’ route planning, shipping dynamics adjustment and operational decisions, but also help airlines optimize the allocation of limited resource to provide better civil aviation transportation services. Meanwhile, passengers can arrange efficient and economical itineraries based on recent changes upon demand in air passenger traffic forecasts. In addition, unmanned check-in and highly intelligent baggage handling are the future development trend toward the intelligent airport construction, and the allocation and scheduling of resources in different airport scenarios are closely rela
Data Loading...
