Multi-horizon shutdown forecast

CF — three honest horizons

How the current-regime shutdown-risk level for CF reads over 1 day, 7 days, and 30 days. Each horizon uses its own XGBoost model with per-horizon SHAP attribution and a 90% conformal interval. These are current-regime risk signals, not onset predictions — see the scope note below.

Generated 2026-08-13 09:01 UTC · model multi-horizon-h-v1 · raw JSON

Probabilities

1 day

23.5%

90% interval [14%, 33%]

7 days

58.8%

90% interval [40%, 78%]

30 days

30d

95.2%

90% interval [45%, 100%]

What this forecast is — and is not

The 7-day forecast is a current-regime risk signal: it reliably tells you which countries are currently in a sustained internet-blocking regime. It is not a shutdown-onset predictor — it does not reliably call a new shutdown before it happens.

On an honest forward-temporal split (train on the past, test only on the strictly-future window) the production model scores AUC 0.589 on its raw label — near chance.
The label target_7day is a 7-day sliding window, so it is 98.9% autocorrelated day-to-day. A trivial predict-yesterday baseline scores AUC 0.957 — high numbers here mean “what is blocked stays blocked,” not predictive skill.
On the rows where a shutdown actually begins (transitions) the forecast scores AUC ~0.33 — below chance.

Use it to see where censorship is entrenched today and to read the SHAP drivers + conformal interval — not as an early-warning siren. Read the full honest re-evaluation →

Consistency check

OK — monotonicP(1d) ≤ P(7d) ≤ P(30d)

The three horizons are internally consistent: longer windows capture at least the risk of shorter windows. This is the expected behavior — a 30-day window must contain any 7-day or 1-day shutdown.

23.5% ≤ 58.8% ≤ 95.2%

Top-5 SHAP features per horizon

Each horizon has its own learned drivers. Positive SHAP values push the prediction up; negative values push it down. Features differ across horizons because near-term risk responds to acute signals, while month-out risk responds to slower structural factors.

Horizon	Rank	Feature	SHAP
1-day	#1	week_of_year	-0.569
	#2	day_of_week	+0.141
	#3	risk_tier	+0.095
	#4	incident_count_7d	-0.063
	#5	gdelt_unrest_30d	-0.041
7-day	#1	week_of_year	-0.636
	#2	recent_shutdown	+0.131
	#3	month	-0.085
	#4	block_rate_roll30_mean	-0.060
	#5	critical_incident_7d	-0.057
30-day	#1	week_of_year	-0.490
	#2	critical_incident_7d	+0.486
	#3	risk_tier	+0.403
	#4	recent_shutdown	-0.108
	#5	month	-0.060

Honest caveats

Each horizon is a separate XGBoost model with its own features and its own honest evaluation. LOCO AUC across spotlight countries: 1d 0.91 · 7d 0.88 · 30d 0.84.
30-day forecasts inherently have wider conformal intervals (more time = more uncertainty). A wide interval is not a bug — it's honesty.
These numbers are not guarantees. A 70% probability does not mean a shutdown is certain; a 20% probability does not mean you're safe.
See /atlas/multi-horizon for the cross-country index, or /atlas/models for the full model registry.

/atlas/forecast/cf — 7-day calibrated forecast with drivers
/cf — CF country profile
/atlas/multi-horizon — all spotlight countries with 30d probability
/v1/forecast/CF/multi-horizon — raw JSON

Probabilities

Consistency check

Top-5 SHAP features per horizon

Honest caveats

Related