ChinaCN
stable (+2.3pp)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.
Peak day
14.8%
d27 · 2026-07-16
Floor day
1.4%
d6 · 2026-06-25
30-day delta
+2.3pp
d30 vs d1 probability
30-day trajectory with 90% conformal band
model trajectory_v1mean P(shutdown by day)90% conformal bandpeak day
Drivers (SHAP top 3 from the 7-day model — same features feed all horizons)
day 14.0%
2026-06-20
- block_rate_roll7_std-0.009
- week_of_year-0.008
- high_urgency_signals_7d-0.007
day 73.3%
2026-06-26
- block_rate_roll7_std-0.009
- week_of_year-0.008
- high_urgency_signals_7d-0.007
day 145.8%
2026-07-03
- block_rate_roll7_std-0.009
- week_of_year-0.008
- high_urgency_signals_7d-0.007
day 306.3%
2026-07-19
- block_rate_roll7_std-0.009
- week_of_year-0.008
- high_urgency_signals_7d-0.007
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 | 2026-06-20 | 4.0% | [0%, 48%] |
| d7 | 2026-06-26 | 3.3% | [0%, 68%] |
| d14 | 2026-07-03 | 5.8% | [0%, 75%] |
| d30 | 2026-07-19 | 6.3% | [0%, 85%] |
Spotlight countries