A Decision–Support Tool for Airline Yield Management Using Genetic Algorithms

Abstract

Airline yield management has gained widespread acceptance in recent years. Yield management is used to estimate the number of passengers belonging to each fare class in order to maximize revenue—to increase profits. Forecasts of future booking for different classes and the fare for each class are assumed fixed and known. The complexity of the problem increases as additional attributes such as the effect of continued flights on pricing, ticket cancellations, and overbooking are considered. In addition, demand varies with time. Hence, to make the problem realistic, the dynamic nature of demand has to be accounted for in the model. The focus of this article is to develop a decision–support tool to estimate the number of seats allocated to each fare class in the yield management problem. This problem is formulated as a linear integer programming model. Genetic algorithms (GAs) are used as a solution technique. The model is coded using C programming language. The decision–support tool considers the effect of time–dependent demand, ticket cancellations, and overbooking policy. The results are consistent with expectations.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 14 citations exist upstream.