Churn prediction for SaaS product users

Overview

Customer churn, in simple words, is a measure of the number of customers who cancel their subscriptions after a certain billing period. This is a pain point that is visible in almost all SaaS businesses as it is far more efficient to retain existing customers than to acquire new customers. Our Saas client was working to increase their customer base and their brand loyalty by offering loyalty programs to their long standing customers. They wanted to design a system to identify a customer's subscription intent and retention by analyzing their patterns and addressing this was critical to their success

Challenge

To solve this problem, we had to analyze the engagement of the customer on the platform by inspecting various parameters like customer profile, product features used, spending patterns on the website, etc. The client's enormous customer data had to be classified according to their purchase, usage patterns and an alert system had to be integrated along with the subscription patterns. If a customer is identified as a potential candidate to cancel his subscription, then customized customer retention programs that can be offered to him can depend on his purchase and usage patterns.

Solution

We started the data acquisition phase of the project by collecting the customer sales records from their MySQL database. Some of the details that we acquired include the sign-in date, monthly purchases on the platform, frequent product features, duration of activity on the website, etc. We then converted this multi-feature dataset into appropriate feature vectors to make it amenable to ML training. Predicting if a customer will continue to utilize the products is a classic example of a Classification problem in Supervised Machine Learning. We then studied the performance of various Classification algorithms like k-NN, Linear SVM, and AdaBoost on this vectorized data set. It was observed that the Linear SVM classifier performed the best in terms of both accuracy and execution time. We packaged the ML model as a self-contained analytic tool that our clients can use on a periodic basis to identify and address the customer churn problem effectively. The analytic tool ingested the MySQL records and produced reports that predict customer churn.

Impact

We are able to help our clients to increase their customer retention by nearly 10 % within a short period of 6 months. This project was developed within an 8-week time frame. The Linear SVM-based ML model was predicting customer churn at an accuracy of 97%. The brand loyalty shown by their customer retention also increased their customer base via referrals and retention programs

Technology stack