Enterprise AI Administration
Churn Propensity Model (legacy)
Model Details · Telecom AI Model Registry
Model Details
Churn Propensity Model (legacy)
Algorithm: Logistic regressionRETIRED
- Code
MDL-CHURN-LEGACY- Version
- v2.0
- Owner
- Head of Customer Analytics
- Governance owner
- Model Risk Committee
Governance configuration shown for review and validation. Read-only.
Business purpose
Previous churn model kept for comparison
Production-recommended design specification. This record does not mean the model has been trained, fitted, deployed or validated.
Technical specification
- Model family
- —
- Algorithm
- Logistic regression
- Implementation library
- —
- Model type
- —
- Explainability method
- —
Implementation governance
- Governance status
- RETIRED
- Implementation status
- NOT IMPLEMENTED
- Validation status
- SUPERSEDED
- Lifecycle stage
- Retired
- Current performance
- Not yet measured
- Refresh cadence
- None
- Last reviewed
- 31 Mar 2026
- Next review due
- —
- Historical sample reference
- AUC 0.76 — earlier sample figure, kept for provenance only; not a validated model result.
Business
- Mission area
- Churn & Retention
- Decision journey
- Churn & Retention
- Target variable
- Churn probability
- Output
- Historic scores only
Input features
Feature summary
Usage, tenure, recharge
Related Intelligence
Linked governed records
KPIs (0)
None recorded.
Business rules (0)
None recorded.
Formulas (0)
None recorded.
Source mappings (0)
None recorded.
Simulation models (0)
None recorded.