Search for: All records

In this paper, we aim to address a relevant estimation problem that aviation professionals encounter in their daily operations. Specifically, aircraft load planners require information on the expected number of checked bags for a flight several hours prior to its scheduled departure to properly palletize and load the aircraft. However, the checked baggage prediction problem has not been sufficiently studied in the literature, particularly at the flight level. Existing prediction approaches have not properly accounted for the different impacts of overestimating and underestimating checked baggage volumes on airline operations. Therefore, we propose a custom loss function, in the form of a piecewise quadratic function, which aligns with airline operations practice and utilizes machine learning algorithms to optimize checked baggage predictions incorporating the new loss function. We consider multiple linear regression, LightGBM, and XGBoost, as supervised learning algorithms. We apply our proposed methods to baggage data from a major airline and additional data from various U.S. government agencies. We compare the performance of the three customized supervised learning algorithms. We find that the two gradient boosting methods (i.e., LightGBM and XGBoost) yield higher accuracy than the multiple linear regression; XGBoost outperforms LightGBM while LightGBM requires much less training time than XGBoost. We also investigate the performance of XGBoost on samples from different categories and provide insights for selecting an appropriate prediction algorithm to improve baggage prediction practices. Our modeling framework can be adapted to address other prediction challenges in aviation, such as predicting the number of standby passengers or no-shows. 

Auto-carriers are widely used to ship automobiles by land from origins to destinations. To enable the compact storage of multiple automobiles, auto-carriers are specially designed such that automobiles can only be loaded and unloaded through a common exit of an auto-carrier, which complicates the automobile loading and unloading operations. This study is motivated by the lack of consensus in the automobile shipping literature regarding whether reloading operations should or should not be prohibited while auto-carriers are en-route. The impact of a loading policy on auto-carrier shipping is not well understood in the literature. We thus examine two types of loading policies (namely reloading prohibited versus allowed), and design network-based optimization methods for each resulting policy variant. We then conduct extensive numerical experiments based on the data from the Southeast region of the USA to investigate the impact of a loading policy on automobile shipping operations through a trade-off analysis between solution quality and computational burden. We find that two proposed policy variants when reloading is allowed can achieve a desirable compromise between cost efficiency and computational effort. A full-scale analysis involving 10 auto-carriers with various capacities further confirms that with these policy variants, substantial cost savings are achieved with reasonable computation effort. The research findings from this article are expected to inform the choice of an appropriate auto-carrier loading policy for automobile transportation companies.