The Pre-Print Cohort Read
Heading into the print, the live cohort_analyze pull on BABA returned n=223 historical analogs with a consensus score of 0.46. The 5-day forward median was +0.07% with IQR [-3.03%, +1.83%] and hit-rate 51%. The 10-day median was -0.28% with IQR [-3.93%, +3.55%]. The dominant 5-day feature was spy_ret_60d (negative direction, importance 1.35).
What Actually Printed
Print-day close: $141.12, prior close $145.81. Day-over-day change: -3.22% (-4.69). Intraday range: $138.61 – $143.98.
Cohort vs. Reality — The Verdict
The -3.22% reaction sits in the cohort's lower IQR — bear bucket realized. The dominant feature (spy_ret_60d) didn't deliver in the direction the bull thesis required, and the analog set's negative-skew bucket is where the print landed.
- n=223, 5d median +0.07%, IQR [-3.03%, +1.83%]
- Conformal bucket boundaries: p10 -6.45% / p90 +4.37%
- Top 5d feature: spy_ret_60d (negative direction, importance 1.35)
- Actual reaction: -3.22%; verdict: lower IQR realization
The Calibration Lesson
For BABA, the calibration verdict is: lower IQR realization. The cohort's structured features (spy_ret_60d dominant) provided the directional read; the realized magnitude lands relative to that read at the bucket described above. Agent systems should retrieve the post-print cohort 24-48 hours after the close — the chart shape will have stabilized, the feature attribution sharpens, and the forward 5-10 day continuation distribution becomes actionable.