Application of machine learning to cluster hotel booking curves for hotel demand forecasting

Accurate demand forecasting is integral for data-driven revenue management decisions of hotels, but an un- precedented demand environment caused by COVID-19 pandemic has made the forecasting process more difficult. This study aims to propose a new approach for daily hotel demand forecasting by using clusters of stay dates generated from historical booking data. This new approach is fundamentally different from traditional forecasting approaches for hotels that assume the booking curves and patterns tend to be similar during the trailing period approach. In this study, historical booking curves are clustered by a machine learning algorithm using an auto-regressive manner and the additive pickup model is used to forecast daily occupancy up to 8 weeks. The efficacy of a new forecasting approach is tested using real hotel booking data of three hotels and results show that forecasts of hotel demand are more accurate when they are generated at cluster-level for all forecasting horizons.