Customer churn is a well-known issue in most sectors, there are various reasons why customers leave banks such as customers aren't getting the results they want, customer service needs improvement, customers believe your competitors can do a better job, customers no longer see the value in bank’s product, and customers believe your product is too expensive or too cheap. Hence it’s critical to develop a perfect predictive model designed in support of customer churn that could be used to formulate a customer retention strategy. This topic is much more important in markets where competition is high and acquiring new customers is more difficult than retaining existing customers. There is a need to build a Bank customer churn/no churn analysis system with best performance and accuracy that will be of great use in banking enabling them to prevent revenue loss, reduce marketing and sales costs and improve the quality of customer service. Coupled with Business Intelligence (BI) tools like Tableau, business executives can make sense of big data. The research focuses on using the machine learning model random forest to help the machine learning model evaluation and interpretability for customer churn analysis in having bank account and are associated with the credit card services, even though multiple models are employed for this analysis.