To calculate the health score, we give each customer's event(which we collect using Intercom) a weight that reflects the impact it has on the likelihood churn, then multiply the weight by the event count, and sum them up. In many existing tools, the weights are determined by gut. 😮
Use data, not your gut!
We love data. We don't have confidence using gut to determine which attributes or events contribute the most for a customer to churn. We find that using machine learning to analyze data gives us the most accurate result. 🤖