Estimating unconstrained customer choice set demand : a case study on airline reservation data

A good demand forecast should be at the heart of every Revenue Management model. Yet most demand models do not incorporate customer choice behavior under offered alternatives. We are using the ideas of customer choice sets to model the customer's buying behavior. The demand estimation method, as described in Haensel and Koole (2011), is based on maximum likelihood and the expectation maximization (EM) algorithm. The main focus of the paper is the application case on real airline reservation data. The reservation data, consisting of the airline's daily flight offers, is used to unconstrain the underlying customer demand in terms of price sensitivity. Using this demand information per choice sets, the revenue manager obtains a clear view of the real underlying demand. -- customer choice behavior ; demand estimation and unconstraining ; revenue management