Exploring Data Visualization to Analyze and Predict Customer Loyalty in Banking Sector with Ensemble Learning

Abstract

Customer loyalty or customer churn, also known as customer attrition, refers to the phenomenon whereby a customer leaves a company. Some studies confirmed that acquiring new customers can cost five times more than satisfying and retaining existing customers. There are a lot of benefits that encourage the tracking of the customer churn rate. Customer value analysis and customer churn predictions will help marketing programs target more specific groups of customers. Churn's prediction could be a great asset in the business strategy for retention applying before customers' exit. In this paper, the banking sector's churn data is used and explores the data with Python data visualization packages such as Matplotlib, Seaborn, and the very new Plotly. This paper aims to identify and visualize which factors contribute to customer churn and to build a prediction model using Ensemble Learning Algorithm. Compare the system accuracy with each model and visualize the results. Preferably based on model performance, choose the model and that will make easier for organizations to target the customers with more chances to become churn. Thus it will allow avoiding loss of revenue of the corresponding organization.