Enterprise AI Administration
ARPU Uplift Model
Model Details · Telecom AI Model Registry
Model Details
ARPU Uplift Model
Algorithm: XGBoostAPPROVED DESIGN
- Code
MDL-ARPU-UPLIFT- Version
- v2.4
- Owner
- Head of Pricing & Revenue
- Governance owner
- Model Risk Committee
Governance configuration shown for review and validation. Read-only.
Business purpose
Estimate incremental ARPU from targeted bundle and pricing actions
Production-recommended design specification. This record does not mean the model has been trained, fitted, deployed or validated.
Technical specification
- Model family
- Gradient Boosted Regression Trees
- Algorithm
- XGBoost
- Implementation library
- XGBRegressor
- Model type
- Regression
- Explainability method
- SHAP TreeExplainer
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
- 03 Sep 2026
- Next review due
- 03 Dec 2026
- Historical sample reference
- R² 0.71 — earlier sample figure, kept for provenance only; not a validated model result.
Business
- Mission area
- Revenue & ARPU
- Decision journey
- Revenue & Profitability
- Target variable
- Incremental ARPU (ZAR)
- Output
- Expected ARPU uplift by segment and offer
Input features
Governed variables, in feature-rank order
- 1.average_monthly_revenueAverage billed service revenue over the last 3 months.
- 2.Average recharge amountMean recharge value
- 3.data_usage_change_30d_pctChange in data MB, last 30 days vs prior 30 days.
- 4.offer_response_scoreLikelihood of accepting a retention or upsell offer (0–1).
- 5.Plan typePrepaid, hybrid or postpaid
Related Intelligence
Linked governed records
KPIs (1)
Business rules (1)
Formulas (1)
Source mappings (3)
Simulation models (1)