Enterprise AI Administration
Fraud Pattern Discovery Model
Model Details · Telecom AI Model Registry
Model Details
Fraud Pattern Discovery Model
Algorithm: DBSCANAPPROVED DESIGN
- Code
MDL-FRAUD-DISC- Version
- v0.1
- Owner
- Revenue Assurance
- Governance owner
- AI Governance Board
Governance configuration shown for review and validation. Read-only.
Business purpose
Discover new fraud patterns as dense clusters and outliers
Production-recommended design specification. This record does not mean the model has been trained, fitted, deployed or validated.
Technical specification
- Model family
- Density-Based Clustering
- Algorithm
- DBSCAN
- Implementation library
- DBSCAN
- Model type
- Unsupervised Density-Based Clustering
- Explainability method
- Cluster / outlier profile
- Cluster selection method
- Density parameter validation
- Distance / membership method
- Neighborhood-density / epsilon 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
- Fraud & Revenue Assurance
- Decision journey
- Fraud & Revenue Assurance
- Target variable
- —
- Output
- Pattern clusters and outliers for analyst review
Input features
Governed variables, in feature-rank order
- 1.fraud_anomaly_scoreUnsupervised anomaly score on calling and recharge behaviour (0–1).
- 2.duplicate_recharge_countRecharges reusing a voucher or repeating within 60 seconds, last 7 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
Related Intelligence
Linked governed records
KPIs (2)
Business rules (2)
Formulas (0)
None recorded.
Source mappings (0)
None recorded.
Simulation models (1)