Enterprise AI Administration
NPS Driver Model
Model Details · Telecom AI Model Registry
Model Details
NPS Driver Model
Algorithm: Elastic Net Regression (benchmark: Multiple Linear Regression)APPROVED DESIGN
- Code
MDL-NPS-DRIVER- Version
- v1.4
- Owner
- Head of Customer Experience
- Governance owner
- Model Risk Committee
Governance configuration shown for review and validation. Read-only.
Business purpose
Explain drivers of NPS movement
Production-recommended design specification. This record does not mean the model has been trained, fitted, deployed or validated.
Technical specification
- Model family
- Regularized Linear Regression
- Algorithm
- Elastic Net Regression (benchmark: Multiple Linear Regression)
- Implementation library
- ElasticNet
- Model type
- Regression / Driver Analysis
- Explainability method
- Coefficient interpretation; SHAP optional where supported
Implementation governance
- Governance status
- APPROVED DESIGN
- Implementation status
- MODEL DEVELOPMENT REQUIRED
- Validation status
- VALIDATION REQUIRED
- Lifecycle stage
- Design
- Current performance
- Not yet measured
- Refresh cadence
- Monthly
- Last reviewed
- 28 Aug 2026
- Next review due
- 28 Nov 2026
- Historical sample reference
- R² 0.66 — earlier sample figure, kept for provenance only; not a validated model result.
Business
- Mission area
- Customer Experience
- Decision journey
- Customer Experience
- Target variable
- NPS
- Output
- Driver contributions to NPS change
Input features
Governed variables, in feature-rank order
- 1.Customer experience sentiment scoreSentiment of care interactions
- 2.Complaint count 30dComplaints in last 30 days
- 3.network_quality_scoreExperienced network quality for the subscriber's serving sites (0–100).
- 4.Dropped call rateShare of the subscriber's calls dropped
- 5.Data session success rateSuccessful data sessions share
Related Intelligence
Linked governed records
KPIs (1)
Business rules (1)
Formulas (1)
Source mappings (3)
Simulation models (0)
None recorded.