Customer Churn Prediction for a Software-as-a-Service Inventory Management Software Company: A Case Study in Thailand

Abstract

Software-as-a-Service is the fast growth and high market values as a new emerging online business. Customer churn is a critical measure for this business. Thus, this paper focuses on seeking a customer churn prediction model for a Software-as-a-Service inventory management software company in Thailand which is facing a high churn rate. This paper executes the prediction models with four machine learning algorithms: logistic regression, support vector machine, decision tree and random forest. The random forest model is capable to provide lowest error with 10-fold cross validation average scores of 91.6% recall and 92.6% F1-score. Moreover, feature importance scores can highlight useful insights of case-study that business metrics are significantly related to churn behavior. As a result, this paper is beneficial to the case-study company to help indicate real churn customer and enhance the effectiveness in executive decision and marketing campaign.