Leveraging Artificial Intelligence for Personalized Guest Experiences in Hotel Management
Annotatsiya
The fast financial growth is leading to a substantial growth in the tourism industry. Traditional HMS (hotel management software), which was primarily focused on economic aspects, is not serving the purpose for comprehensive data management. Guest experience and satisfaction were the forefront of HMS research for the last couple of decades and IoT presents the HMS the potential to lower the operating cost while enhancing the guest experience. The web, parking lots, competent assistance, front desk, amenities, price, residence, spot, and cleanliness are the criteria that are taken into account to create the evaluations. The difficulty in evaluation is further increased if the traditional methods are adopted for predicting the hotel reviews with low predictive power. Specifically, deep learning (DL) techniques are employed to evaluate the assessments that help customers to choose improved accommodation. In this work, there were multiple prediction methods based on classification to predict attributes, such as a support vector machine-based deep learning (SVM-DL) and convolutional neural network-based deep learning (CNN-DL). By using the TripAdvisor page, a well-known US records company, the performance of the system is evaluated according to the criteria in the study, and the result of the study shows that the CNN-DL method is superior to the other method in terms of error level and categorization performance. The results obtained express that the theoretical and intellectual achievements of the research could be also used for the enhancement of the effectiveness of the proposed approach and the formulation of response mechanisms. Moreover, although it can be concluded that the potentiality of IoT for HMS is still being deeply examined, the researchers often assume conclusions on IoT deployments that may be quickly applied to hotels and tend to ignore the possibility as a main market.