Simulation & Prediction
Scenario Simulation Workspace
Compare current state, no action, recommended, upside and downside scenarios for one journey or issue.
Journey
Fraud & Revenue Assurance
KPI under simulation
Fraud + revenue leakage
Current
USD 1.9M
Target
No stored target
Scenario outcome cards
Base case
Current trajectory with in-flight initiatives only.
- Stated outcome
- Monthly SIM-box leakage: $0.3M
- Risk / trade-off
- —
- Fraud + revenue leakage in 6 mo
- USD 1.9M ACTUAL
Bulk blocking
Block all high-confidence SIMs.
- Stated outcome
- $0.3M / month avoided
- Risk / trade-off
- Small false-positive risk
- Fraud + revenue leakage in 6 mo
- USD 1.13M SCENARIO
Blocking + test-call programme
Add international test-call monitoring.
- Stated outcome
- $0.4M / month avoided
- Risk / trade-off
- Vendor cost $30k/month
- Fraud + revenue leakage in 6 mo
- not modelled
Manual review
Investigate SIMs individually.
- Stated outcome
- $0.1M / month avoided
- Risk / trade-off
- Slow; fraud migrates
- Fraud + revenue leakage in 6 mo
- not modelled
Not stored for this journey: No Action, Downside. Shown as a gap rather than invented.
Scenario comparison — stated value vs cost/risk (USD M)
Amounts parsed from each scenario's stored results; ★ = recommended. Non-monetary outcomes plot as zero.
Risk / return matrix
Top-left = high value for low stated cost/risk.
Fraud + revenue leakage — actual vs scenario paths
Same projection as the journey Predict stage and the Forecasting page. Open full forecast →
Comparison table
| Scenario | Role | Assumptions | Projected KPI (6 mo) | Stated impact | Risk / trade-off |
|---|---|---|---|---|---|
| Base case | Current State | Current trajectory with in-flight initiatives only. | USD 1.9M | Baseline | — |
| Bulk blocking | Recommended | Block all high-confidence SIMs. | USD 1.13M | $0.3M / month avoided | Small false-positive risk |
| Blocking + test-call programme | Upside | Add international test-call monitoring. | — | $0.4M / month avoided | Vendor cost $30k/month |
| Manual review | Alternative | Investigate SIMs individually. | — | $0.1M / month avoided | Slow; fraud migrates |
Scenario → decision
Recommended scenario: Bulk blocking — $0.3M / month avoided; trade-off: Small false-positive risk.
No decision is saved here; the decision is recorded in the journey at Decide.
Source data, assumptions, methodology & limitations
Source data
- Telecom KPI data (current period, target, prior)
- Historical KPI trend data (monthly history Apr–Sep 2026)
- Scenario library (assumptions, results, recommended flag)
- Value realization records (expected / actual value)
- Evidence records
Assumptions
- No action: continues the 6-month stored trend (-0.13 per month).
- Recommended action: reverses the trend at the same monthly rate (no stored target).
- Scenario outcomes, costs and risks are as stored for each scenario.
Methodology
- Scenarios of the selected journey are ordered Current State → No Action → Recommended → Upside → Downside → Alternatives.
- With an originating issue, alternatives sharing no words with the issue move to the bottom of the table.
- Projected KPI per scenario uses the shared deterministic forecast; only Current State, No Action and Recommended are modelled.
Limitations
- Scenario outcomes are governed figures stored with each scenario — they are not re-computed by a simulation engine.
- Forecasts are straight-line projections of six stored months; they ignore seasonality, shocks and interactions between measures.
- Many KPIs have no stored target; where absent, the recommended path reverses the trend at the same monthly rate.
- No downside scenario is stored for any journey; downside coverage is shown as a gap rather than invented.
| Evidence type | Item | Source |
|---|---|---|
| model output | SIM-box detection output 1,240 SIM-box incidents flagged; 91% detection rate. | Revenue assurance data |
| methodology | Fraud & Revenue Assurance methodology Run CDR anomaly detection; Reconcile usage, rating and billing; Value prevented losses. | Finance Planning Dataset |