name: Churn Predictor
slug: churn-predictor
description: Predict customer churn risk using behavioral signals, engagement data, and predictive analytics
category: customer-support
complexity: complex
version: "1.0.0"
author: "ID8Labs"
triggers:
- "churn prediction"
- "churn risk"
- "customer retention"
- "at-risk customers"
- "churn analysis"
- "retention modeling"
tags:
- churn
- prediction
- retention
- analytics
- customer-success

Churn Predictor

Expert churn prediction system that identifies at-risk customers before they leave using behavioral signals, engagement patterns, and predictive analytics. This skill provides structured workflows for building churn models, monitoring risk signals, and executing retention interventions.

Churn is the silent killer of growth. By the time a customer announces they're leaving, it's often too late. This skill helps you identify churn risk early when intervention can still make a difference, prioritize retention efforts, and systematically reduce churn.

Built on data science best practices and customer success methodologies, this skill combines leading indicator analysis, risk scoring, and intervention playbooks to predict and prevent churn before it happens.

Core Workflows

Workflow 1: Churn Signal Identification

Map the behaviors that predict churn

1. Behavioral Signals
   | Signal Type | Examples | Risk Level |
   |-------------|----------|------------|
   | Usage Decline | 30%+ drop in logins, sessions, actions | High |
   | Feature Abandonment | Stopped using key features | Medium-High |
   | Engagement Drop | No response to emails, missed meetings | Medium |
   | Support Patterns | Spike in tickets, negative sentiment | High |
   | Billing Issues | Failed payments, downgrade requests | High |

2. Account Signals

3. Champion departure (key user leaves)
4. Company layoffs or restructuring
5. Merger/acquisition announcements
6. Budget cuts affecting your category
7. Competitor evaluation signals

8. Contract not renewed on auto-renew

9. Relationship Signals

10. NPS score decline (9-10 → 7 or below)
11. Missed QBRs or check-ins
12. Unresponsive to outreach
13. Escalated support issues

14. Negative sentiment in communications

15. Time-Based Signals

16. Approaching renewal (90/60/30 days)
17. End of trial or pilot
18. Anniversary of bad experience
19. Post-implementation plateau
20. Seasonal usage patterns

Workflow 2: Risk Scoring Model

Build a composite churn risk score

1. Score Components
   ```
   Churn Risk Score =
   (Usage Score × 0.30) +
   (Engagement Score × 0.25) +
   (Support Score × 0.20) +
   (Relationship Score × 0.15) +
   (Account Score × 0.10)

Scale: 0-100 (higher = more at risk)
```

1. Usage Score Factors
2. Login frequency vs. baseline
3. Feature adoption breadth
4. Active users vs. licensed seats
5. Time in product

6. Core action completion

7. Engagement Score Factors

8. Email open/click rates
9. Meeting attendance
10. Resource downloads
11. Training completion

12. Community participation

13. Risk Categories
    | Score | Risk Level | Action |
    |-------|------------|--------|
    | 0-20 | Low | Standard monitoring |
    | 21-40 | Moderate | Proactive outreach |
    | 41-60 | Elevated | Intervention needed |
    | 61-80 | High | Urgent save attempt |
    | 81-100 | Critical | Executive escalation |

Workflow 3: Cohort & Trend Analysis

Understand churn patterns across customer segments

1. Cohort Analysis
2. Analyze by signup month/quarter
3. Track retention curves over time
4. Identify cohorts with worse retention
5. Correlate with product/market changes

6. Find patterns in successful cohorts

7. Segment Analysis

8. By customer size (SMB/Mid/Enterprise)
9. By industry vertical
10. By use case/persona
11. By acquisition source

12. By pricing tier

13. Churn Timing Patterns

14. When in customer lifecycle does churn occur?
15. Renewal vs. mid-contract churn
16. Time from warning signs to churn
17. Seasonal patterns

18. Correlation with contract length

19. Leading Indicator Validation

20. Track signals → churn correlation
21. Calculate signal lead time
22. Measure false positive rate
23. Refine scoring weights
24. A/B test interventions

Workflow 4: Alert & Escalation System

Surface risk at the right time to the right people

1. Alert Triggers
2. Score crosses threshold (e.g., into "elevated")
3. Rapid score increase (10+ points in 7 days)
4. Critical signal detected (payment failed, champion left)
5. Renewal approaching with elevated risk

6. Multiple signals converging

7. Escalation Matrix
   | Risk Level | Owner | Escalation | Response SLA |
   |------------|-------|------------|--------------|
   | Moderate | CSM | None | 5 days |
   | Elevated | CSM | Manager copy | 48 hours |
   | High | CSM + Manager | VP briefed | 24 hours |
   | Critical | Manager | VP/Exec sponsor | Same day |

8. Alert Content

9. Customer name and risk score
10. Specific signals triggering alert
11. Score trend (improving/declining)
12. Renewal date and ARR at risk

13. Recommended actions

14. Alert Channels

15. Slack/Teams notifications
16. Email digests
17. CRM dashboards
18. Weekly risk reports
19. Executive summaries

Workflow 5: Intervention Playbooks

Systematic approaches to save at-risk customers

1. Intervention Matching
   | Root Cause | Intervention |
   |------------|--------------|
   | Low adoption | Training, onboarding redo |
   | Technical issues | Engineering escalation, workarounds |
   | Value unclear | ROI analysis, executive alignment |
   | Champion left | Relationship rebuild with new stakeholders |
   | Pricing concerns | Discount, plan adjustment, payment terms |
   | Competitive | Feature comparison, roadmap preview |

2. Save Play Execution

3. Diagnose root cause (don't assume)
4. Match intervention to cause
5. Assign owner and resources
6. Set clear timeline and milestones

7. Track outcome (saved, lost, reason)

8. Intervention Tactics

9. Urgent Call: Same-day executive outreach
10. Health Check: Comprehensive account review
11. Training Blitz: Intensive enablement sessions
12. Success Sprint: Focused value delivery
13. Executive Alignment: VP/C-level engagement

14. Commercial Discussion: Pricing/terms adjustment

15. Outcome Tracking

16. Save rate by risk level
17. Save rate by intervention type
18. Time from intervention to resolution
19. Reasons for unsuccessful saves
20. Long-term retention of saved accounts

Quick Reference

Best Practices

Signal Selection

• Focus on behaviors you can observe
• Validate correlation with actual churn
• Use leading indicators (not lagging)
• Combine multiple signal types
• Weight by predictive power

Scoring Model

• Start simple, add complexity gradually
• Calibrate weights with historical data
• Validate with blind holdout testing
• Recalibrate quarterly
• Document methodology

Alert Design

• Don't alert on every score change
• Focus on actionable thresholds
• Include context in alerts
• Route to right person
• Avoid alert fatigue

Intervention

• Diagnose before prescribing
• Match intervention to root cause
• Set clear success criteria
• Track outcomes rigorously
• Learn from failures

Model Maintenance

• Review accuracy monthly
• Retrain with new churn data
• Adjust for product changes
• Update as customer base evolves
• Document false positives/negatives

Churn Signals Library

Usage Signals

Engagement Signals

Support Signals

Relationship Signals

Risk Report Template

Weekly At-Risk Summary

# Churn Risk Report: Week of [Date]

## Summary
- Accounts at elevated risk or above: [X]
- Total ARR at risk: $[Amount]
- New alerts this week: [X]
- Risk trending up: [X accounts]
- Risk trending down: [X accounts]

## Critical Risk (81-100)
| Account | ARR | Score | Key Signals | Owner | Action |
|---------|-----|-------|-------------|-------|--------|
| [Name] | $X | 87 | [Signals] | [CSM] | [Status] |

## High Risk (61-80)
[Same format]

## Elevated Risk (41-60)
[Same format]

## Interventions in Progress
| Account | Started | Intervention | Progress |
|---------|---------|--------------|----------|
| [Name] | [Date] | [Type] | [Status] |

## Outcomes This Week
- Saved: [X accounts, $ARR]
- Lost: [X accounts, $ARR, reasons]
- De-escalated: [X accounts]

Red Flags

• Model overfit: Perfect on training data, poor on new data
• Signal lag: Indicators trigger too late for intervention
• False positive fatigue: Too many alerts that aren't real risk
• Missing signals: Key churn predictors not tracked
• Score opacity: Team doesn't understand why scores change
• Intervention mismatch: Same playbook for different problems
• No feedback loop: Not learning from save attempts
• Data quality: Missing or stale underlying data

Model Validation Metrics