Churn forecast has been broadly explored in the fields of telecom, finance, retail, pay TV and banking. Lessening agitate is significant because procuring new clients is more costly than holding existing clients. Few studies have been conducted in airlines for customer churn prediction using machine learning algorithms. Many studies in churn prediction used Practice, socio-economic and demographic variables, customer lifetime values and the usage of Recency, Frequency and Monetary (RFM) attributes in churn prediction. Few studies have used service quality dimensions but possibly due to a privation of alertness of their helpfulness as forecasters of churn [37]. In this study, we use some dimensions of the Service Quality (SERVQUAL) Model to select features from the dataset. The nominated functions are given to the ensemble-classification techniques like Boosting and Bagging. We use a dataset on South West Airlines obtained from GitHub and conduct experiments of supervised ML procedures further down the identical cross-validation and assessment setup, permitting an open-minded assessment across algorithms. Our investigation reveals some leading service quality indicators that might help airlines predict who might stop flying soon due to their perception of their service quality. These insights could provide actionable suggestions as to how to avoid having the customers leave and go to another airline. This will enable the companies to improve their quality of service and formulate appropriate retention strategies targeted to each category. Lastly, the enactment of the projected model is assessed grounded on the subsequent metrics like ‘ROC’, Sensitivity, F-Measure, specificity, ‘Precision’ and ‘Accuracy’ and it is recognized that the Projected system deliberate with joining feature assortment based on some aspects of SERVQUAL model with the ensemble -Bagging classification techniques produced the best results with classification accurateness of 94% compared to any single model and other feature reduction techniques in Weka.