Modeling Airlines’ Route Selection Decisions Under Competition: A Discrete-Games-Based Model

摘要

To analyze the effects of policies within the air transportation network, there is a need to model how policies affectthe decisions made by airlines. Because airline decision making is based on proprietary information, such models needto rely on openly available data sources. In this paper, openly available data from the Bureau of TransportationStatistics are used to develop a predictive model of airline route selection decisions. The proposed model accounts forairline competition and models parameters such as operating cost, which can be influenced by policymakers. Thispaper illustrates the model using a dataset from two major airlines in U.S. domestic air transportation network. Thedataset and the cost model are used for Bayesian estimation of model parameters, which are then used to predict theeffects of cost and demand on the evolution of the network topology. The proposed model is found to be more accuratethan competing models that do not consider the competition. From the estimates obtained on preference parameters,it is found that decreasing the operating cost and increasing the market demand increase the probability of operatingservice on the route for airlines, and the operating cost has a greater effect than market demand and route distance onthe route selection decisions.