Enhancing Hospitality Management Through Ml-Based Cancellation Prediction

Abstract

Hotel booking cancellations present a significant challenge for the hospitality industry, as they create uncertainty in room occupancy and disrupt operational planning. A high rate of cancellations can lead to revenue loss and inefficient resource utilization. This study focuses on predicting whether a customer will cancel a hotel booking using a machine learning approach. Specifically, a Multi-Layer Perceptron (MLP) Classifier, a type of deep learning model, is employed to capture complex patterns within hotel booking data. The model is trained and optimized by tuning key hyperparameters, including the number of hidden layers, number of neurons, activation functions, and learning rate, to enhance predictive accuracy. By accurately forecasting booking cancellations, the proposed system enables hotel managers to optimize room allocation, improve resource management, minimize financial losses, and support informed decision-making. Overall, this approach demonstrates the potential of machine learning techniques in improving efficiency and service quality within the hospitality sector.