META · > 7% below its 21-day MA · forward 21 sessions · recency window from 2021-01-01 · half-life 9mo · de-clustered ≥21d
Now: -10.1% vs the 21-day MA · 5th pctile (2021+) · 4th all-time
Close 556.71 · MA 619.00 · IN BREACH now · all-time range -28.1% … +36.9%
Forward returns by regime
Median forward return (% positive) at 2 / 5 / 8 / 11 / 15 / 21 sessions, conditioned on each market regime — and the recency-weighted read (the headline). Watch how the shape shifts as the window tightens toward now.
Full historyPost-CovidAI eraRallyRecency-wtdbaseline
Horizon
Full historyn=43
Post-Covidn=22
AI eran=11
Rallyn=9
Recency-wtdn=22
2 sessions
+0.7% 52%
+0.4% 52%
+0.7% 50%
-1.0% 38%
+1.5% 52%
5 sessions
+0.7% 60%
+0.8% 62%
+0.4% 60%
-0.0% 50%
+2.1% 59%
8 sessions
+1.4% 62%
+2.3% 67%
+1.1% 60%
-0.5% 50%
+1.4% 56%
11 sessions
+1.2% 57%
+1.5% 52%
+6.0% 60%
+1.5% 50%
+6.1% 54%
15 sessions
+0.7% 52%
+2.9% 52%
+6.4% 70%
+4.4% 62%
+5.8% 58%
21 sessions
+1.7% 57%
+5.6% 57%
+8.9% 70%
+8.9% 62%
+9.4% 59%
Regime delta: the recency-weighted 21-day median is +7.7 pts vs the full-history read — the recent regime is markedly stronger here.
Headline is recency-weighted (faster 9-month half-life) over 22 post-2021 events. Regime windows: AI era from Apr 1 2023 · Rally from the Oct 30 2023 bottom. Tight regimes carry few events (see the n per column) — read them with the recency-weighted line, which keeps sample by fading rather than cutting.
Forward 21d · median
+9.4%
mean +4.2%
% positive
59%
22 events
vs baseline
+7.0 pts
base +2.4% / 62% pos
Range
-33% … +16%
25th -4.7% · 75th +9.4%
Path · max-gain
+10.1%
median MFE in window
Path · max-draw
-7.6%
median MAE in window
Every event · outcome over time
Each dot is one de-clustered event at its date; height is the forward 21-session return. Gold-ringed = post-2021 — if there are few gold rings, the signal is a pre-Covid-regime artifact.
By decade: 2010s 182020s 24
The event log
Event date
Stretch
Fwd 21d
Max gain
Max draw
2012-07-16
-10.0%
-27.9%
+3.9%
-29.1%
2012-08-14
-15.6%
+1.6%
+4.0%
-13.0%
2012-10-10
-8.1%
+2.2%
+18.3%
-3.4%
2013-02-04
-7.6%
-2.3%
+3.3%
-4.4%
2013-03-25
-7.1%
+3.9%
+11.5%
+0.0%
2013-05-24
-8.9%
-0.2%
+1.0%
-5.8%
2013-11-11
-8.2%
+6.9%
+8.8%
-3.0%
2014-03-24
-7.1%
-4.3%
+1.2%
-11.5%
2015-08-21
-8.6%
+8.0%
+11.0%
-4.6%
2016-01-13
-7.5%
+6.9%
+20.6%
-1.3%
2016-11-03
-7.2%
-2.1%
+3.5%
-4.1%
2018-03-22
-8.0%
+0.6%
+2.3%
-7.7%
2018-07-26
-13.3%
-0.9%
+5.4%
-3.0%
2018-09-06
-7.5%
-3.2%
+3.9%
-3.2%
2018-10-24
-7.4%
-9.8%
+3.9%
-9.9%
2018-11-23
-8.5%
+1.9%
+10.1%
-5.8%
2019-06-03
-11.0%
+18.8%
+18.8%
+0.0%
2019-08-05
-8.5%
+3.0%
+4.6%
-2.2%
2020-02-27
-9.1%
-17.4%
+3.5%
-23.1%
2020-06-26
-7.1%
+6.5%
+13.6%
+0.0%
2020-09-17
-8.4%
+4.4%
+8.4%
-2.6%
2021-01-12
-7.0%
+7.7%
+12.3%
-2.2%
2021-09-22
-7.6%
-0.4%
+3.0%
-5.7%
2021-12-01
-7.5%
+8.3%
+11.5%
-1.2%
2022-01-21
-8.5%
-33.3%
+6.5%
-33.3%
2022-02-22
-20.3%
+5.6%
+7.2%
-7.6%
2022-04-20
-8.9%
-4.6%
+11.5%
-12.7%
2022-05-24
-8.3%
-6.1%
+9.7%
-14.0%
2022-06-28
-9.0%
+0.0%
+14.0%
-1.6%
2022-08-30
-7.1%
-13.2%
+7.6%
-14.5%
2022-09-29
-9.8%
-27.3%
+2.8%
-28.2%
2022-10-28
-23.7%
+10.3%
+18.0%
-10.4%
2023-08-18
-7.2%
+7.7%
+10.1%
+0.0%
2023-10-26
-7.4%
+16.1%
+18.4%
+0.0%
2024-04-25
-11.7%
+8.3%
+9.1%
-2.5%
2024-07-17
-9.0%
+16.3%
+16.3%
-1.9%
2025-03-04
-7.8%
-8.7%
+2.6%
-9.9%
2025-04-03
-11.0%
+12.7%
+12.7%
-8.8%
2025-10-30
-7.8%
-3.8%
+0.0%
-11.6%
2026-03-20
-7.2%
+12.7%
+16.0%
-11.4%
2026-05-11
-7.4%
-4.7%
+6.1%
-4.7%
2026-06-25
-7.9%
+9.4%
+25.5%
+0.0%
Read it honestly. The recency-weighted read leans on 22 post-2021 events (half-life 9mo); the full-history column carries 43. The regime delta shows how far recent behaviour has drifted from the long base rate. De-clustered by a 21-session gap; overlapping windows remain. A context gauge, not a mechanical signal.
Computed live from adjusted-close history (yfinance). Forward return = close-to-close over 21 sessions from each event. MFE/MAE = max favorable / adverse excursion within the window. Educational research, not investment advice.