Predict customer churn daily using ML or LLM models and notify via Slack/email

by Oneclick AI Squad ✓ · 153 views · created 2026-02-26 · CRM, AI Summarization

What this workflow does

This workflow has 16 nodes and runs on a schedule (cron 0 2 * * *). Along the way it connects Postgres.

How it runs

Trigger: On a schedule (cron 0 2 * * *).

1. Fetch active customer profiles (HTTP Request): calls an HTTP API
2. Fetch customer activity logs (30 days) (HTTP Request): calls an HTTP API
3. Fetch transaction history (90 days) (HTTP Request): calls an HTTP API
4. Merge: merges the data from its input branches
5. Engineer behavioral features (Code): runs custom JavaScript code
6. Call ML churn prediction model (HTTP Request): calls an HTTP API (POST)
7. Score and classify churn risk (Code): runs custom JavaScript code
8. Route by risk level (Switch): routes items into 3 branches
9. Create retention campaign task (HTTP Request): calls an HTTP API (POST)
10. Store churn predictions in database (Postgres): uses Postgres

…plus 5 more steps. See the full node list below.

Services it uses

Postgres

Before you upgrade to n8n 3.0

Nodes used (8)

• Schedule Triggern8n-nodes-base.scheduleTrigger
• HTTP Requestn8n-nodes-base.httpRequest
• Mergen8n-nodes-base.merge
• Coden8n-nodes-base.code
• Switchn8n-nodes-base.switch
• Postgresn8n-nodes-base.postgres
• Filtern8n-nodes-base.filter
• Send Emailn8n-nodes-base.emailSend

From the author

This n8n workflow runs daily to analyze active customer behavior, engineers relevant features from usage and transaction data, applies a machine learning or AI-based model to predict churn probability, classifies risk levels, triggers retention actions for…

View the original on n8n.io → Check your own copy