Increasing competition and implementation of revenue management strategies in the airline industry have boosted accurate demand forecasting to maximize revenue. While most previous demand forecasting studies have focused on final booking demand of flights, this study develops a novel Transformer-based deep learning model to forecast flight advance bookings at daily granularity, named Flightformer. The proposed model considers the competition effect from other flights on the same route and determines the hyperparameters with Bayesian optimization. Subsequently, real flight advance booking data for nearly four years are used to evaluate the model performance. The results of the comparative experiment and ablation study show that Flightformer significantly outperforms the baseline and variant models. Moreover, the transferability of Flightformer on the other new route is examined.
A model for forecasting flight advance booking demand with competition effect
Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024) ; 2024 ; Kuala Lumpur, Malaysia
Proc. SPIE ; 13184
2024-07-05
Conference paper
Electronic Resource
English
Model of an advance-booking system for highway trips
Online Contents | 2008
|Model of an advance-booking system for highway trips
Online Contents | 2008
|Booking Demand Response Transport online
British Library Online Contents | 2011
Advance Automotive Ltd: Web Content Management & Booking Project
British Library Conference Proceedings | 2006
|