This thesis is aimed at recommending suitable hotels to the customers using the data collected from the website booking.com. In this thesis, data from Stockholm is chosen as an example, and statistical modeling is applied. We propose recommended hotels based on their rankings in terms of the scores of the hotels. The ranking score is derived by using eneralized linear mixed models. Box-Cox transformation is applied further to improve the previous analysis. Separate group analysis indicates that the ranks between different reviewer groups are significantly different. Model evaluation is executed via Cross-validation method by calculating the classification accuracies for all models. The best model is found based on theclassification accuracy, and we recommend the top 10, top 15 and top 20 hotels from the best model in this thesis.