EX

Simulation & Prediction

Forecasting

Historical actuals with run-rate, no-action and recommended-action projections against target.

Latest actual

ACTUAL

99.62%

Run-rate (6 mo)

FORECAST

99.62%

No action (6 mo)

FORECAST

99.49%

Recommended (6 mo)

SCENARIO

99.7%

Target

TARGET

99.7%

Network availability — Network Performance & Risk

Solid = stored actuals (Historical KPI trend data). Dashed = deterministic projections in the shaded period. Band = ±1σ of historical residuals around the no-action line, widening with horizon. Direction of good: higher.

Forecast table

PeriodTypeActualRun-rateNo actionRecommendedSpread (±1σ)
Apr 26ACTUAL99.74%
May 26ACTUAL99.71%
Jun 26ACTUAL99.7%
Jul 26ACTUAL99.68%
Aug 26ACTUAL99.66%
Sep 26ACTUAL99.62%
Oct 26FORECAST—99.62%99.6%99.63%99.59% – 99.61%
Nov 26FORECAST—99.62%99.58%99.65%99.57% – 99.59%
Dec 26FORECAST—99.62%99.55%99.66%99.54% – 99.56%
Jan 27FORECAST—99.62%99.53%99.67%99.51% – 99.55%
Feb 27FORECAST—99.62%99.51%99.69%99.49% – 99.53%
Mar 27FORECAST—99.62%99.49%99.7%99.47% – 99.51%

Source data, assumptions, methodology & limitations

Source data

  • Telecom KPI data (current period, target, prior)
  • Historical KPI trend data (monthly history Apr–Sep 2026)

Assumptions

  • Run-rate baseline: holds the latest stored actual flat.
  • No action: continues the 6-month stored trend (-0.02 per month).
  • Recommended action: closes the gap to the stored target (99.7%) over 6 months.

Methodology

  • Least-squares straight line through 6 stored months (slope -0.022 per month).
  • Residual standard deviation σ = 0.008; spread = σ × √(months ahead).
  • Identical arithmetic feeds Decision Journey Stage 5 — Predict.

Limitations

  • 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.
Forecast horizon: 6 months (Oct 2026 – Mar 2027)Model status: deterministic arithmetic — no AI or machine-learning model.
Evidence typeItemSource
model output

Congestion forecast

214 sites forecast to exceed 85% utilisation within 90 days.

OSS network data
model output

SIM-box detection output

1,240 SIM-box incidents flagged; 91% detection rate.

Revenue assurance data
methodology

Network Performance & Risk methodology

Aggregate availability and KPIs from network counters; Classify outages by root cause; Score sites by risk and revenue exposure.

Finance Planning Dataset
assumption

FX assumption

All figures in USD at a constant planning rate.

Finance Planning Dataset
model output

Churn propensity scores

48k high-value subscribers scored above 60% churn propensity.

CRM
limitation

Regulatory data lag

Regulator returns lag by one quarter; current quarter is estimated.

Regulatory Reporting Store