# Why use machine learning to compute health scores?

**How are health scores calculated?**

To calculate the health score of a customer, each event(which we collect using Intercom) is assigned a weight that reflects the impact it has on the likelihood churn, then multiply the weight by the event count, and sum them up and normalize. In many existing tools, the weights are determined by the gut. 😮<br>

**Use data, not your gut!**

We love data. We don't have confidence using the gut to determine which events contribute the most for a customer to churn. We find that using machine learning to analyze data gives us the most accurate result. 🤖


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.getalvis.com/master.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.