Intelligent decision support system using nested ensemble approach for customer churn in the hotel industry

Since customer retention costs much less than attracting new customer, the problem of customer churn is a major challenge in various fields of work and particularly Hotel Industry. In this research, a solution based on an intelligent decision support system using text mining and nested ensemble techniques is presented, which combines the advantages of stacking and voting methods. In the proposed system, after the text mining of the data collected from the hotels of Kish Island, the effective feature selection is done using the gravity search algorithm. In the first level of nested ensemble technique method, stacking deep learning methods are used. Voting is used in the MetaClassifier section, which includes Random Forest, Xgboost and Naive Bayes methods. The results of the implementation and comparison of the proposed system, show that the performance of the proposed system has increased the accuracy by 0.04 compared to the best existing method.