Enterprise AI Administration
Usage Pattern Segmentation Model
Model Details · Telecom AI Model Registry
Model Details
Usage Pattern Segmentation Model
Algorithm: K-MeansAPPROVED DESIGN
- Code
MDL-SEG-USAGE- Version
- v0.1
- Owner
- Growth Analytics
- Governance owner
- AI Governance Board
Governance configuration shown for review and validation. Read-only.
Business purpose
Group subscribers by usage pattern to plan growth offers
Production-recommended design specification. This record does not mean the model has been trained, fitted, deployed or validated.
Technical specification
- Model family
- Centroid-Based Clustering
- Algorithm
- K-Means
- Implementation library
- KMeans
- Model type
- Unsupervised Clustering
- Explainability method
- Cluster profile / centroid; distance to centroid
- Cluster selection method
- Elbow / Silhouette analysis
- Distance / membership method
- Euclidean distance
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
- —
- Next review due
- —
Business
- Mission area
- Subscriber Growth
- Decision journey
- Subscriber Growth
- Target variable
- —
- Output
- Usage segment per subscriber
Input features
Governed variables, in feature-rank order
- 1.data_usage_change_30d_pctChange in data MB, last 30 days vs prior 30 days.
- 2.voice_usage_change_30d_pctChange in voice minutes, last 30 days vs prior 30 days.
- 3.usage_pattern_deviationDeviation of current usage from the subscriber's 90-day profile (z-score).
- 4.Roaming usage flagAny roaming usage in month
- 5.Digital activity scoreApp and wallet engagement score
Related Intelligence
Linked governed records
KPIs (1)
Business rules (1)
Formulas (1)
Source mappings (3)
Simulation models (1)