Customer churn prediction ML pipeline diagram
This is a worked example. Wavelength built the diagram below from the description on this page. Nobody drew it by hand.
What was said
Product usage events and billing data land in the Databricks lakehouse. A feature pipeline builds the customer features every night. The churn model scores every account. If an account's churn risk is above 70 percent, the account is pushed to Salesforce and the customer success manager gets a task. MLflow tracks each model version, and the data science team retrains the model every month.
The diagram
What is in this flow
- Systems: Feature Pipeline, Churn Model, Salesforce and MLflow.
- Data stores: Databricks Lakehouse.
- People and teams: Customer Success Manager and Data Science Team.
- Decisions: Churn Risk >70%?.
- Size: 9 steps and 8 connections.
Mermaid code
Copy this into any Markdown file, GitHub README, or Mermaid Live to render the same flow.
flowchart TD
n1(["Product Usage & Billing Data")]
n2[("Databricks Lakehouse")]
n3{{"Feature Pipeline"}}
n4{{"Churn Model"}}
n5{"Churn Risk >70%?"}
n6{{"Salesforce"}}
n7("Customer Success Manager")
n8{{"MLflow"}}
n9("Data Science Team")
n1 -->|land in| n2
n2 -->|feeds| n3
n3 -->|builds features| n4
n4 -->|scores| n5
n5 -->|Risk >70%| n6
n5 -->|Risk >70%| n7
n4 -->|tracks| n8
n9 -->|retrain| n4Map your own process
Describe your version out loud, or paste the transcript of a call. Wavelength draws the flow as you talk, and you can edit it by voice, by prompt, or by hand.
Every new account starts with 14 days of Pro. No card needed.