Hindcast demonstration · Humanitarian & displacement

Hindcast: would trend continuation have beaten 'no change' on Sudan's IDP total?

IOM DTM's March 2026 round reports a national IDP total below 9.5 million

This is a hindcast, not a live predictionThis record was constructed after the outcome was known, using only information available at its stated data cutoff, to demonstrate how Warconomy scores forecasts. It is excluded from live predictive performance on the track record.
ForecastVerifiedresolvedIssued · data through trend-continuation-v1 v1.0
Warconomy forecast8,500,000–9,500,000
8,500,0009,500,000

Plausible range — this is not a claim of precision beyond what the underlying method supports.

Issued
Data cutoff
Horizon
425 days
Resolves by
Epistemic class
Forecast (modeled, not observed)
Evidence status
verified

How this resolves

Resolves TRUE if DTM's March 2026 Sudan round reports a national IDP total below 9,500,000.

Resolution source: IOM Displacement Tracking Matrix, Sudan displacement and return snapshots

Assumptions

  • Cutoff-date information only: DTM's recorded peak was 11,585,384 IDPs in January 2025.
  • Returns would begin to outpace new displacement as some areas stabilized.

Leading indicators to watch

  • DTM return figures relative to new-displacement figures

What would make this wrong

  • A major new offensive displacing over a million people.

Naive baseline comparison

BaselineNo-change naive baseline
Baseline saidThe March 2026 total remains at the January 2025 peak of 11,585,384.
Baseline outcomeBaseline was wrong

What actually happened

DTM's 29 March 2026 round recorded an estimated 8,936,175 IDPs — a 23% decline from the peak, inside the forecast's 8.5-9.5 million plausible range. The no-change baseline was wrong by roughly 2.65 million.

Observed value8,936,175
Interval covered outcomeYes
Directionally correctYes
Scored

The prediction above is preserved exactly as issued — this outcome sits alongside it and never replaces it.

Methodology

Takes the recent pace of change in an official series and keeps it going, assuming nothing dramatic happens. Simple, transparent, and easy to check — but it will miss sudden shocks.

Uncertainty: A plausible-range bracket, widened for longer horizons, reflecting the compounding risk that the constant-rate assumption breaks down. Not a statistical confidence interval — labeled as plausible-range throughout.

Validation: Compared against a no-change naive baseline on historical published points where two or more comparable rounds exist. See /forecast-track-record for the hindcast demonstrations.

Full model card: Trend continuation (rule-based) v1.0.

Sources

SourceTypeLink
IOM — Displacement Tracking Matrix, SudanIntergovernmentaldtm.iom.int/sudan

All forecast fields (accessible table)

Every field of this forecast record, as published.
FieldValue
Forecast IDhc-2026-03-sudan-idp-decline
Target variableIOM DTM Sudan total internally displaced persons
Target eventIOM DTM's March 2026 round reports a national IDP total below 9.5 million
Prediction8,500,000–9,500,000
Issue date2025-01-28
Data cutoff2025-01-28
Horizon (days)425
Resolution date2026-03-29
Resolution sourceIOM Displacement Tracking Matrix, Sudan displacement and return snapshots
Statusresolved
Epistemic classforecast
Evidence statusverified
Modeltrend-continuation-v1 v1.0
HindcastYes — not a live prediction

Machine-readable: /forecasts/data.json

Explore next