CHURN RATE PREDICTION USING MACHINE LEARNING

Abstract

Customer Churn refers to a situation in which a customer has terminated a relationship with a company, and this is an expensive issue. Customers are the fuel that stimulates a company. The loss of customers affects sales. Moreover, it is much more difficult and expensive to win new customers than to keep existing customers. As a result, organizations need to focus on reducing customer churn. Machine Learning can be advantageous in solving this problem. For many businesses that offer subscription based services, it’s critical to both predict customer churn and explain what features relate to customer churn. Older techniques such as logistic regression can be less accurate than newer techniques such as deep learning, which this project demonstrates i.e an ANN in R with the keras package. For many business problems, it’s equally important to explain what features drive the model, which is why LIME package is used for explainability. LIME results are cross-checked with a Correlation Analysis using the corrr package for increased accuracy. The R tool has represented the large dataset churn in form of graphs which depicts the outcomes in various unique pattern visualizations. The Churn Factor is used in many functions to depict the various areas or scenarios where churners can be distinguished. Artificial Neural Networks (ANN) are now a staple within the sub-field of Machine Learning called Deep Learning. Deep learning algorithms can be vastly superior to traditional regression and classification methods (e.g. linear and logistic regression) because of the ability to model interactions between features that would otherwise go undetected. The challenge becomes explainability, which is often needed to support the business case. Keras and LIME provides best of both techniques.