Estimating Air-Cargo Overbooking Based on a Discrete Show-Up-Rate Distribution

  • Authors:

  • Andreea Popescu;Pinar Keskinocak;Ellis Johnson;Mariana LaDue;Raja Kasilingam

  • Affiliations:

  • School of Industrial and Systems Engineering, Georgia Institute of Technology, 765 Ferst Drive, Atlanta, Georgia 30332;School of Industrial and Systems Engineering, Georgia Institute of Technology, 765 Ferst Drive, Atlanta, Georgia 30332;School of Industrial and Systems Engineering, Georgia Institute of Technology, 765 Ferst Drive, Atlanta, Georgia 30332;Sabre Airline Solutions, 1 East Kirkwood Boulevard, Southlake, Texas 76092;Sabre Airline Solutions, 1 East Kirkwood Boulevard, Southlake, Texas 76092

  • Venue:
  • Interfaces
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

Most airlines overbook their actual capacity (for both passengers and cargo) because part of the booked demand often does not show up at the flight departure. A key element of overbooking is a model that accurately predicts the show-up rate of the current bookings. Given the increasing importance of cargo within their business, most major airlines now scrutinize estimates of show-up rates for cargo bookings. The current practice is to apply the same methodology to the cargo sector as in the passenger business. We investigate the suitability of the current practice, and based on the results, we propose an alternate show-up-rate estimator for cargo and demonstrate its benefits. Tested on real-world data from a major airline as well as on simulated data, the study shows that improved estimation of the show-up rate can improve profits and customer service.