The ability to forecast traffic and to size the operation accordingly is a determining factor, for airports. However, to realise its full potential, it needs to be considered as part of a holistic approach, closely linked to airport planning and operations. To ensure airport resources are used efficiently, accurate information about passenger numbers and their effects on the operation is essential. Therefore, this study explores machine learning capabilities enabling predictions of aircraft load factors. The rationale behind the logic used stems from the assumption that using past traffic statistics in a form of historic load factor may not be sufficient, especially at times of high traffic volatility such as during regional bank holidays. Therefore, exploration efforts were made to parameterize some novel predictive elements that could provide passenger demand predictions at different granularity levels. The investigation has been successful and through the use of gradient boosting technique, the model, including 9 significant predictors was created. The load factor predictions per flight perform highly accurately with an average mean absolute error around 10 percentage points. In principle, this achievement outscores any other related work conducted in this domain to date. On top of that, the model itself is scalable and can be applied to any airport in the network as applied to use cases within the presented paper.
Miroslav Spak, Lorenzo Frigerio, Lenka Hanakova, Vladimir Socha, Rocio Barragan Montes, Vincent Treve, Flight Load Factor Predictions based on Analysis
of Ticket Prices and other Factors, In Proc. of the SESAR Innovation Days, December 2025.
Click here to access the paper.