Laurie GARROW

Utility-Maximizing Models of Airline Passengers’ Show, No Show, and Standby Behavior

Utility-based choice models of airline passengers’ rescheduling behavior are presented. Distinct from previous studies of travel rescheduling estimated from stated preference data, these models use revealed preference data. Variables are derived from proprietary data sources that span booking, ticketing, flight/itinerary schedule, frequent flier membership class, and check-in information. Linking these distinct data sources, not previously done, enabled development of the first itinerary-based no show model in the airline industry.

The model predicts the probability a carrier’s booked passenger will show, no show, or standby for an earlier or later itinerary with the same carrier. The model captures day-of-departure rescheduling processes and explores differences based on booking class, frequent flier status and affiliation, schedule attributes of the carrier of interest and its competitors differentiated by level of service, and other factors. Particular emphasis is placed on understanding how standby behavior differs by booked fare class, frequent flyer status, and inbound versus outbound itineraries. Multinomial logit (MNL) and nested logit (NL) results estimated for domestic U.S. itineraries in March 2001 and March 2002 explore shifts in rescheduling behavior due to tighter security measures and lower load factors occurring after September 11, 2001.