Enterprise AI Administration
Network Incident Risk Model
Model Details · Telecom AI Model Registry
Model Details
Network Incident Risk Model
Algorithm: XGBoostAPPROVED DESIGN
- Code
MDL-NET-INCIDENT- Version
- v1.9
- Owner
- Head of Network Operations
- Governance owner
- Network Risk Board
Governance configuration shown for review and validation. Read-only.
Business purpose
Predict service degradation and site risk
Production-recommended design specification. This record does not mean the model has been trained, fitted, deployed or validated.
Technical specification
- Model family
- Gradient Boosted Decision Trees
- Algorithm
- XGBoost
- Implementation library
- XGBClassifier
- Model type
- Classification / Incident Probability
- 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
- Daily
- Last reviewed
- 22 Sep 2026
- Next review due
- 22 Oct 2026
- Historical sample reference
- Precision@50 0.78 — earlier sample figure, kept for provenance only; not a validated model result.
Business
- Mission area
- Network Performance & Risk
- Decision journey
- Network Performance & Risk
- Target variable
- Site degradation probability (7 days)
- Output
- Ranked at-risk sites and regions
Input features
Governed variables, in feature-rank order
- 1.Site congestion indexPeak utilisation score per site
- 2.Outage countOutages per site in last 30 days
- 3.capacity_utilization_pctBusy-hour capacity utilisation of a site.
- 4.critical_alarm_countCritical alarms raised on a site, last 7 days.
Related Intelligence
Linked governed records
KPIs (1)
Business rules (2)
Formulas (1)
Source mappings (3)
Simulation models (1)