Airlines frequently deal with unexpected disruptions, which must be resolved to resume operations. Decision-support tools help airlines with disruption management. However, the computation of an integrated recovery solution considering aircraft, crew, and passengers at the same time is a hard problem to solve, requiring long computational times to compute globally optimal solutions. On the other hand, faster sequential approaches have been proposed, which recover one resource at a time, but these compromise the quality of the recovery solution. This paper presents a real-time decision-support approach to solve the integrated airline recovery problem. The model simultaneously recovers the schedule and allocates aircraft and cockpit crew pairs to the flights while minimizing additional incurred costs. Passengers are implicitly recovered by considering missed connections and prescribing alternative itineraries. Recovery actions include delaying and canceling flights, swapping aircraft, swapping and deadheading crew, or using reserve crew. A machine-learning ranking algorithm reduces the problem's computational complexity by selecting a subset of the resources that are likely to be involved in the recovery plan, such that only part of the network is considered. The decision-support tool was evaluated on disruption scenarios of one of the largest airlines in the world: Delta Airlines. The results show that the machine learning selection reduces the average computational time 15-fold compared to the integrated recovery model that uses the complete network. Good quality aircraft and crew recovery solutions could be computed in under two minutes for 98% of the disruption cases tested.