China CN
stable (+4.5pp)Follow the model’s 30-day path. Read the probability and uncertainty together.
30-day trajectory with 90% conformal band
model trajectory_v1mean P(shutdown by day)90% conformal bandpeak day
Peak day
21.9%
d26 · 2026-11-01
Floor day
1.4%
d4 · 2026-10-10
30-day delta
+4.5pp
d30 vs d1 probability
Drivers (SHAP top 3 from the 7-day model — same features feed all horizons)
day 13.9%
2026-10-07
- block_rate_roll7_std-0.082
- high_urgency_signals_7d-0.059
- week_of_year-0.053
day 75.6%
2026-10-13
- block_rate_roll7_std-0.082
- high_urgency_signals_7d-0.059
- week_of_year-0.053
day 149.1%
2026-10-20
- block_rate_roll7_std-0.082
- high_urgency_signals_7d-0.059
- week_of_year-0.053
day 308.5%
2026-11-05
- block_rate_roll7_std-0.082
- high_urgency_signals_7d-0.059
- week_of_year-0.053
Honest caveats
- Per-horizon XGBoost stacked into a trajectory — not a true joint distribution.
- Conformal bands are absolute-residual q90 from LOCO predictions on 18 eval countries.
- Long horizons (h>=14d) have wider effective uncertainty than the conformal q90 suggests; the same lag features feed all horizons.
- Bands floor at [0,1]; probabilities below 0.05 are at the model's noise floor.
- SHAP attribution above is from the 7-day point model. The trajectory uses 30 separate per-horizon XGBoost models that share the same feature set; we have not yet computed per-horizon SHAP.
Sample horizons
| Day | Date | P(shutdown) | 90% interval |
|---|---|---|---|
| d1 | 2026-10-07 | 3.9% | [0%, 48%] |
| d7 | 2026-10-13 | 5.6% | [0%, 70%] |
| d14 | 2026-10-20 | 9.1% | [0%, 78%] |
| d30 | 2026-11-05 | 8.5% | [0%, 87%] |
Spotlight countries
About this view
30-day day-by-day shutdown-risk trajectory. Each point is a per-horizon XGBoost prediction (h=1..30) with a 90% conformal band derived from absolute LOCO residuals. Peak risk highlighted.