Evolving forecast combination structures for airline revenue management

This work presents findings of a collaboration project between Bournemouth University and Lufthansa Systems AG, a company providing revenue management software for airline carriers, to increase net booking forecast accuracy by modifying one of its components, the cancellation forecast.

Abstract

Forecasting is at the heart of every revenue management system, providing necessary input to capacity control, pricing and overbooking functionalities. For airlines, the key to efficient capacity control is determining the time of when to restrict bookings in a lower-fare class to leave space for later booking high-fare customers. This work presents findings of a collaboration project between Bournemouth University and Lufthansa Systems AG, a company providing revenue management software for airline carriers. The main aim is to increase net booking forecast accuracy by modifying one of its components, the cancellation forecast. Complementing an available set of three traditional individual algorithms, an additional method is presented and added to the method pool. Furthermore, diversification of model parameters and level of learning is discussed to increase the number of individual forecasts even further. Finally, the evolution of forecast combination structures is investigated and shown to be beneficial on an airline data set.