Predicting off-block delays: A case study at Paris-Charles de Gaulle International Airport

Thibault Falque (1, 2) , Bertrand Mazure (2) , Karim Tabia (2)

1 Exakis Nelite
2 CRIL - Centre de Recherche en Informatique de Lens

Punctuality is a sensitive issue in large airports and hubs for passenger experience and for controlling operational costs. This paper presents a real and challenging problem of predicting and explaining flight off-block delays. We study the case of the international airport Paris Charles de Gaulle (Paris-CDG) starting from the specificities of this problem at Paris-CDG until the proposal of modelings then solutions and the analysis of the results on real data covering an entire year of activity. The proof of concept provided in this paper allows us to believe that the proposed approach could help improving the management of delays and reduce the impact of the resulting consequences.

Mots clés: Machine Learning; Application; Real Time Delay; Machine Learning Application Real Time Delay

Domaines: Intelligence artificielle [cs.AI]

Thibault Falque, Bertrand Mazure, Karim Tabia. Predicting off-block delays: A case study at Paris-Charles de Gaulle International Airport. 15th International Conference on Agents and Artificial Intelligence (ICAART 2023), Feb 2023, Lisbonne, Portugal. pp.180-189. ⟨hal-03986693⟩