Software-as-a-service (SaaS) companies generate revenues by charging recurring subscription fees for using their software services. The fast growth of SaaS companies is usually accompanied with huge upfront costs in marketing expenses targeted at their potential customers.
Customer retention is a critical issue for SaaS companies because it takes 12 months on average to break-even with the expenses for a single customer. This project, conducted by MSDS students Yizhe Ge, Shan He and Jingyue Xiong, describes a methodology for helping SaaS companies manage their customer relationships.
They investigated the time dependent software feature usage data, for example, login numbers and comment numbers, to predict whether a customer would “churn” within the next three months. The
study compared model performance across four classification algorithms. The XGBoost model yielded the
best results for identifying the most important software usage features and for classifying customers as either churn type or non-risky type.
The feature importance output from the XGBoost model can help SaaS companies identify the most significant software features to launch more effective marketing campaigns for prospective customers.