An Integrated Capacity Allocation and Dynamic Pricing Model Designed for Air Cargo Transportation

Air cargo plays a pivotal role in the global economy by facilitating international trade. Air cargo companies must meticulously plan and price their limited capacity efficiently to gain a competitive advantage and enhance their profitability. To mitigate the risk of empty aircraft, companies can sell capacity through prior agreements or offer capacity for free sales to generate additional revenue. The intricate nature of the air cargo industry, coupled with the numerous variables that influence pricing within this sector, renders the dynamic determination of prices a complex and arduous undertaking. This study aims to dynamically determine the price for the free sales capacity. The proposed model addresses three critical issues in air cargo revenue management: capacity allocation, demand forecasting, and dynamic pricing. An integrated structure has been developed in which these three distinct issues are interconnected. In this study, CVaR and ANN models are used for capacity allocation, regression, and time series, and ANN models are used for demand forecasting, while the SARSA algorithm, one of the reinforcement learning algorithms, is used for dynamic pricing. The model is implemented using data from a prominent air cargo company, and the results are interpreted, and recommendations are made for future research.