Markov Chains and an application on hotel businesses

Competition in the tourism sector is increasing day by day, and it is very important for hotel management to know the preference rates of hotels and the factors that affect the preferences, in terms of future marketing strategies. In this sense, determining the preference rates of hotels and their reasons is one of the issues that hotel managements prioritize strategically. The aim of this study is to determine the preference probabilities and the factors affecting preferences of 4 and 5-star hotels with beaches in Mersin province. Firstly, the data of the study were obtained from 410 randomly selected people. After the data were obtained, the study was divided into two parts. In the first part, the preference probabilities of the hotels for the next period and the preference rates of the hotels in the long term were estimated by using the Markov chain method. These estimates were based on considering the current hotel where the participants stayed or if any, the last hotel they stayed. In the second part of the study, the underlying reasons for hotel preferences were determined by using the Hidden Markov model. According to the empirical findings obtained from the first part of the study, the three most preferred hotels in the long term are Ulu Resort Hotel (5*), Liparis Resort Hotel & Spa (5*) and Wonasis Resort & Aqua Hotel (5*), respectively. According to the results of the analysis made in the second part, among the factors affecting the hotel preferences, it was observed that the most important factors affecting the hotel preferences are location, room and facility cleaning, availability of facilities for families with children, and the effectiveness of recommendations/advertisements. It is thought that the results obtained from the study will guide the marketing strategies of the hotels included in the study.