Gauging and foreseeing customer churn in the banking industry : a neural network approach

Project Work presented as the partial requirement for obtaining a Master's degree in Information Management, specialization in Knowledge Management and Business IntelligenceIn today´s highly competitive market where information is easily accessible and with ever decreasing switching costs, customers in any industry hardly hesitate to move their business elsewhere should they find more suitable proposals to accommodate their needs. As such, it is in the best interest of any company to keep a close watch on its customers to monitor any signs of potential churning down the line. Significant headways in the Business Intelligence field have brought forward a great number of tools for knowledge discovery and predictive analytics purposes. This paper proposes a new framework for assessing and predicting customer attrition in one of the biggest Portuguese retail banks. Data mining techniques were employed to study the behavior and patterns of past churners. A set of predictor variables was obtained from this process and used to train a set of predictive models using neural networks. Assessment of the performance of the classifiers was later validated on a sample of current customers in risk of churning. The goal of this project is to provide a new approach to identify potential churners so marketing retention strategies be developed accordingly