The accurate anticipation of passenger demand across specific origin–destination (OD) airport routes is a cornerstone of strategic and operational decision-making within the global aviation sector, including airlines optimizing fleet and route management, airports planning infrastructure development, and regulatory bodies overseeing airspace efficiency. However, conventional forecasting techniques frequently encounter limitations when confronted with the inherent complexities and non-linear interdependencies that characterize air travel demand patterns. These patterns are shaped by an array of dynamic variables, including macroeconomic trends, population dynamics, distinct seasonal variations, and emergent phenomena. This investigation evaluates the utility of Artificial Intelligence (AI) paradigms in constructing predictive models for monthly passenger volumes between international OD airport pairs. This work highlights the ongoing transformative impact of AI methodologies on forecasting tasks within the aviation industry.

The widely used Quality Service Index (QSI) model estimates air traffic by considering attributes such as capacity, connectivity, and travel time, which impact an itinerary market share (MS) in the origin-destination (OD) market. To determine itinerary attractiveness, the conventional QSI model combines these features, weighting them based on their significance and generates a score for each option. The key is therefore to select the optimal combination of weighted attributes that are able to forecast the MS with the desired accuracy. However, traditional QSI models rely on expert knowledge and assume that the traffic generation and allocation is always based in the same market principles, hindering their ability to generalize and identify new features. To address this, the present work, which is part of a research project entitled ERA funded by Red.es, introduces a generalized rationale based on Artificial intelligence using historical data, a challenge that has been faced in the early stages of the project. This approach enables the identification and understanding of key features in the aviation traffic and the development of a forecasting model capable of capturing more complex feature relationships.