Browsing by Author "Contessi, Daniele"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
- Decoding the future: proposing an interpretable machine learning model for hotel occupancy forecasting using principal component analysisPublication . Contessi, Daniele; Viverit, Luciano; Nobre Pereira, Luis; Heo, Cindy YoonjoungAccurate hotel occupancy forecasting is vital for optimizing hotel revenue, yet interpretable machine learning tools lack extensive research. This paper presents a two-step approach utilizing historical and advanced booking data. Principal Components Analysis (PCA) groups similar patterns in booking curves, followed by a pickup forecasting model to predict occupancy. Evaluating the approach using real booking data from three European hotels (2018 -2022), it outperformed two benchmarks: classical additive pickup and clustering-based pickup methods. Empirical results demonstrate the superiority of PCA-based methods across all hotels and forecasting horizons. Additionally, incorporating Average Daily Rates into PCA enhances daily hotel demand forecasts, offering potential for enhanced predictions with business operational information in a low-dimensional space.
- Dynamics of hotel bookings: identifying key drivers of hotel conversion ratePublication . Luchi, Piero; Heo, Cindy Yoonjoung; Nobre Pereira, Luis; Viverit, Luciano; Contessi, DanieleAll hotels receive numerous booking requests every day, either directly or through online travel agencies, but only a small percentage of these requests are converted into reservations. Low conversion rates generate an additional layer of uncertainty into the hotel demand function and pose a challenge for revenue maximization. Consequently, optimizing the conversion rate is a top priority for all hotel managers. Despite its importance, the factors influencing the conversion rate are not yet well understood. This longitudinal study aimed to identify the factors that explain seasonal variations in the conversion rate, providing insights to optimize it. By segmenting stay dates using machine learning algorithms and employing a logistic regression model to predict the probability of conversion per segment, this innovative research proposes a framework for conversion rate optimization. The research note contributes a new data mining methodology that can be implemented in machine learning algorithms to enhance conversion rates