The goal of this work is to investigate the effects of different machine learning methods in hotel booking cancellation process. Hotel booking cancellation is provided a substantial effects on demand management decisions in the hospitality industry. The proposed methodology is also used to analyze a real nonprobability survey sample on the social effects of COVID-19. The results show that the four proposed estimators based on gradient boosting frameworks can improve survey representativity with respect to other classic prediction methods. At the same time, a comparison is made of the effectiveness of these methods for the elimination of biases. In this study, we test the potential of the XGBoost algorithm in the most important methods for estimation that integrate data from a probability survey and a nonprobability survey. To compensate for these biases, researchers have employed a variety of statistical techniques to adjust nonprobability samples so that they more closely match the population. However, the effect of coverage and selection bias in such surveys has undercut their utility for statistical inference in finite populations. In the last years, web surveys have established themselves as one of the main methods in empirical research. The study offers a unique contribution to literature, since it is a live case study, and the information is from the practicing employees of a well-known organization in a hospitality sector from a smart city (Novotel Ambassador Seoul Dongdaemun Hotels and Residences, Seoul, South Korea). The practicing managers of hospitality industry can employ AI enabled robots within the scope of improving and automating the processes that can also offer increased personalization to enhance the stay experience, which is expected in a smart city. Further, with a back-and-forth mapping mechanism based on epistemological principles, the authors made four propositions that lead to the development of a research framework. Through a systematic approach of coding, the authors have identified that deploying AI enabled robots facilitates the automation, information gathering, personalization and seamless service in the hospitality industry of a smart city. Out of 214 employees in the hotel with varied experience and background, 26 interviews are conducted.
The authors have selected employees for interviews since employees listen and witness the guest experience directly. Semistructured interviews have been conducted at Novotel Ambassador Seoul Dongdaemun Hotels and Residences, Seoul, South Korea, to understand the stay experience of guests regarding services offered by AI enabled robots. Therefore, this case study aims to examine and explore artificial intelligence (AI) enabled robots in hospitality industry in order to enhance guest experience in a smart city. To offer a memorable stay experience, the industry has started deploying intelligent robots. The hospitality industry has witnessed numerous changes to enhance the stay experience of guests.
Experiments on synthetic and real-world datasets as well as human evaluations demonstrate the highly promising capabilities of XInsight. XInsight uses a set of design concepts and optimizations to address the inherent difficulties associated with integrating causality into XDA. XInsight is a three-module, end-to-end pipeline designed to extract causal graphs, translate causal primitives into XDA semantics, and quantify the quantitative contribution of each explanation to a data fact. For this purpose, we present XInsight, a general framework for XDA. This way, XDA will significantly improve human understanding and confidence in the outcomes of data analysis, facilitating accurate data interpretation and decision-making in the real world. XDA provides data analysis with qualitative and quantitative explanations of causal and non-causal semantics. This study promotes for the first time a transparent and explicable perspective on data analysis, called eXplainable Data Analysis (XDA). In light of the growing popularity of Exploratory Data Analysis (EDA), understanding the underlying causes of the knowledge acquired by EDA is crucial, but remains under-researched.