Predicting hotel booking cancellations using predictive analytics methods

Abstract

The aim of this dissertation is to provide a comprehensive examination of the impact of hotel booking cancelations and to evaluate the suitability of various machine learning algorithms for predicting and mitigating their effects. It begins by delving into the significance of cancellations for hotels, examining their influence on aspects like revenue loss, diminished room occupancy, and the costs of handling last-minute alterations. The study identifies the various ways in which cancelations can impact hotel revenue and operations, including loss of income, reduced room occupancy, and the costs associated with accommodating last-minute changes. Following this, the study conducts a comparative analysis of various machine learning algorithms for their effectiveness in predicting booking cancelations. The comparison is based on factors such as accuracy, interpretability, and ability to identify the factors that contribute to cancelations. The results of the comparison provide valuable insights into the relative performance of different machine learning algorithms in the context of hotel booking cancelations. The findings suggest that certain algorithms perform better than others in terms of accuracy and interpretability and highlight the importance of considering these factors when selecting an appropriate algorithm for hotel revenue management. Finally, the conclusion of the study highlights the practical applications of the research findings for hotels. By utilizing the insights gained from this study, hotels can improve their revenue management and customer satisfaction by better predicting and managing booking cancelations.