In many application areas such as airlines and hotels a large number of bookings are typically cancelled. Explicitly taking into account cancellations creates an opportunity for increasing revenue. Motivated by this we propose a revenue management model based on Talluri and van Ryzin [27] that takes cancellations into account in addition to customer choice behaviour. Moreover, we consider overbooking limits as these are influenced by cancellations. We model the problem as a Markov decision process and propose three dynamic programming formulations to solve the problem, each appropriate in a different setting. We show that in certain settings the problem can be solved exactly using a tractable solution method. For other settings we propose tractable heuristics, since the problem faces the curse of dimensionality. Numerical results show that the heuristics perform almost as good as the exact solution. However, the model without cancellations can lead to a revenue loss of up to 20%. Lastly we provide a parameter estimation method based on Newman et alii [24]. This estimation method is fast and provides good parameter estimates. The combination of the model, the tractable and well-performing solution methods, and the parameter estimation method ensures that the model can efficiently be applied in practice.

Using five years of data collected from a small and independent hotel this case study explores RMS data as a means to seek new insights into occupancy forecasting. The study provides empirical evidence on the random nature of group cancellations, an important but neglected aspect in hotel revenue management modelling. The empirical study also shows that in a local market context demand differs significantly per point of time during the day, in addition to seasonal monthly and weekly demand patterns. Moreover, the study presents evidence on the nonhomogeneous Poisson nature of the probability distribution that demand follows, a crucial characteristic for forecasting modelling that is generally assumed but not reported in the hotel forecasting literature. This implies that demand is more uncertain for smaller than for larger hotels. The paper concludes by drawing attention to the critical and often overlooked role of exploratory data analysis in hotel revenue management forecasting.

A key step in data-driven decision making is the choice of a suitable mathematical model. Complex models that give an accurate description of reality may depend on many parameters that are difficult to estimate; in addition, the optimization problem corresponding to such models may be computationally intractable and only approximately solvable. Simple models with only a few unknown parameters may be misspecified, but also easier to estimate and optimize. With such different models and some initial data at hand, a decision maker would want to know which model produces the best decisions. In this paper we propose a decision-based model-selection method that addresses this question.

Gerard Loosschilder is a market research practitioner with extensive experience on the client, agency and academic side. Having held the position of Chief Methodology Officer at a highly quantitative research firm, Gerard Loosschilder is comfortable with advanced research approaches including conjoint analysis. Yet, from working at the client side (Philips Electronics) and working with clients, he learned to care most about partnering with businesses to make sure that they understand study results and act on it. That's why Gerard Loosschilder explores creative ways of generating insights and encouraging businesses to act on them. Loosschilder has a PhD from Delft University of Technology, Delft, The Netherlands. Presently, Loosschilder has his own consultancy firm. Zvi Schwartz's scholarly research and industry consulting focus on the core technical and strategic elements of the hospitality revenue management cycle: forecasting, optimization and monitoring, as well as the closely related topics of strategic pricing, and consumer and firm decisions in advanced reservation environments. Recent projects explored novel hotel forecasting approaches, occupancy forecasting accuracy measures, manipulation of hotel competitive sets, overbooking optimization and revenue management performance measures. He received his doctoral degree from Purdue University and holds an MBA and a bachelor's degree in Economics.Paolo Cordella is Manager at the Advanced Analytics Centre of Excellence at LEGO. In his previous role at as consultant at SKIM, a market research agency, he specialized in choice modelling, conjoint analysis and ABSTRACT Using conjoint analysis and choice data from 1492 Dutch participants, this experimental study explores the impact of user interface functionalities on hotels' customer online behavior and the subsequent economic ramifications for both the search engine service providers and their hotel clients. Specifically, it explores the impact of sorting and filtering on the relationship between a hotel's placements on the initial search results booking page and the likelihood of being booked. The findings indicate that the availability of sort and filter functions generates a more balanced distribution of booking choices, as users pay more attention to the hotel characteristics that are subject to sorting and filtering functionality. If the sort and filter functions are applied to price, visitors are more likely to choose cheaper rooms, whereas when applied to customer ratings, visitors are more likely to choose rooms with better ratings. The functions affect the search agenda and consequently the economic value of placement in top positions. In addition, sorting and filtering increase the competitiveness of the search engine because it encourages users to apply additional choice criteria beyond merely relying on the hotel's placement on the search result page.