Forecasting and optimisation for hotel revenue management

Abstract

Over the past decade, revenue management techniques have been extensively developed in the airline and hotel industries. Much of the research has been on the optimisation front, which focuses on finding the optimal seat allocation policy to maximise revenue. There has been, however, less published work on forecasting issues. In this paper, we present a framework for forecasting and optimisation which we apply to the hotel industry. Based on real-life hotel booking data, we utilise various forecasting techniques and compare their performance. Because classical stochastic optimisation models are generally too hard to solve, we present a network flow formulation and report on computational results.