Voidly
Forecast
Atlas · 1d / 7d / 30d forecasts

One country. Three horizons.

Compare current-regime risk at 1, 7 and 30 days. Read the uncertainty ranges; these are not shutdown-onset predictions.

Trained 2026-05-21 · Recommendation: ship_all_three · model info

20 spotlight countries · ranked by 30-day risk

#Country1d7d30d30d range (90%)Cons.
1Iran IR22%36%95%
[45%, 100%]
ok
2China CN22%36%95%
[45%, 100%]
ok
3Russia RU22%36%95%
[45%, 100%]
ok
4Egypt EG36%68%95%
[45%, 100%]
ok
5Venezuela VE36%59%95%
[45%, 100%]
ok
6Belarus BY36%64%95%
[54%, 100%]
ok
7Cuba CU36%59%95%
[45%, 100%]
ok
8Ethiopia ET22%59%95%
[45%, 100%]
ok
9Myanmar MM36%59%95%
[55%, 100%]
ok
10Azerbaijan AZ36%65%95%
[45%, 100%]
ok
11TJ TJ36%59%95%
[45%, 100%]
ok
12Kazakhstan KZ36%65%95%
[45%, 100%]
ok
13Uzbekistan UZ36%65%95%
[53%, 100%]
ok
14AF AF36%59%95%
[45%, 100%]
ok
15Pakistan PK36%68%95%
[45%, 100%]
ok
16Bangladesh BD36%65%95%
[45%, 100%]
ok
17India IN22%49%95%
[45%, 100%]
ok
18Turkey TR36%68%95%
[45%, 100%]
ok
19Saudi Arabia SA36%64%95%
[45%, 100%]
ok
20Turkmenistan TM15%36%70%
[20%, 100%]
ok

Cons. = monotonicity (P(1d) ≤ P(7d) ≤ P(30d)). 30d range = 90% conformal interval.

1d LOCO AUC
0.907
inflated — see scope note
7d LOCO AUC
0.883
inflated — see scope note
30d LOCO AUC
0.845
inflated — see scope note

Why three horizons?

A single 7-day number is what most journalists ask for, but it hides two important things: the current-regime risk level tomorrow, and the operational ceiling over the next month. We train three independent XGBoost models and publish all three with LOCO AUC numbers and per-horizon SHAP attribution. Note: each horizon uses the same target_Nday sliding-window label as the production v1 forecast, so the LOCO AUCs are inflated by label autocorrelation the same way — these are current-regime risk signals, not shutdown-onset predictors. See the onset-skill finding.

The monotonicity check is a free honesty signal: longer windows must contain shorter windows, so if P(1d) > P(30d) the three models are disagreeing and you should treat the headline numbers with caution. See /atlas/models for the full registry, or /methodology for the full pipeline.

Related

About this view

Three honest forecast horizons per country — each with its own XGBoost model, its own SHAP attribution, and its own 90% conformal interval. Click a country for per-horizon detail.

Forecast scope & limitations