Model-based decision support for optimal brochure pricing: applying advanced analytics in the tour operating industry

Abstract

The research presented in this paper is motivated by an industry project conducted with TUI Deutschland, Germany's leading tour operator. We consider the decision problem of optimally determining hotel room prices to be published in the tour operator's brochure, which is usually valid for a half-year period. In practice, this task is performed manually by a large number of pricing specialists, each of whom is in charge of setting up to 100,000 prices. In this paper, we develop an advanced analytics approach to provide decision support for this task. More precisely, we propose a mixed integer linear programming-based approach, involving state-of-the-art methods from data analysis and optimization. In this context, we formally introduce the brochure pricing problem as a new optimization problem and present several alternative mathematical model formulations. The problem incorporates demand-side behavior by including a general attraction model whose parameters can be obtained from past booking data. Furthermore, we present different real-world scenarios of model-based decision support, showing how the brochure pricing problem and some variants thereof can be integrated into the manual decision making process, given the requirement of using standard optimization software. For example, the model-based approach can help the pricing specialist balance the objective of profit maximization and the disadvantage of a very complicated pricing structure.