Predictive and Prescriptive Analytics Toward Passenger-Centric Ground Delay Programs

Ground delay programs (GDPs) comprise the main interventions to optimize flight operations in congested air traffic networks. The core GDP objective is minimize delays, but this may not result optimal outcomes for passengers—especially with connecting itineraries. This paper proposes a novel passenger-centric optimization approach GDPs by balancing and passenger delays large-scale For tractability, we decompose problem using rolling procedure, enabling model’s implementation manageable runtimes. Computational results based on real-world data suggest that our modeling computational framework can reduce significantly at small increases costs through two mechanisms: (i) allocation (delaying versus prioritizing flights) (ii) introduction (holding flights avoid misconnections). In practice, however, itineraries are unknown managers; accordingly, propose statistical learning models predict accordingly. Results show proposed highly robust imperfect knowledge of provide significant benefits even current decentralized environment collaborative decision making.