QQQ/SPY · > 3% below its 65-day MA · forward 21 sessions · recency window from 2021-01-01 · half-life 9mo · de-clustered ≥42d
Now: -3.9% vs the 65-day MA · 5th pctile (2021+) · 3th all-time
Close 0.92 · MA 0.96 · IN BREACH now · all-time range -8.2% … +10.8%
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=25
Post-Covidn=10
AI eran=3
Rallyn=3
Recency-wtdn=10
2 sessions
+0.2% 60%
-0.6% 40%
+0.8% 67%
+0.8% 67%
-1.5% 31%
5 sessions
+0.1% 60%
-0.5% 40%
+0.9% 67%
+0.9% 67%
-0.5% 30%
8 sessions
+0.5% 58%
-0.7% 44%
+1.5% 100%
+1.5% 100%
+0.5% 85%
11 sessions
+0.5% 58%
-0.9% 33%
+1.7% 100%
+1.7% 100%
+1.5% 80%
15 sessions
+0.0% 50%
-0.7% 44%
-0.0% 50%
-0.0% 50%
-0.7% 39%
21 sessions
-0.4% 46%
-0.8% 22%
-0.9% 0%
-0.9% 0%
-0.8% 9%
Regime delta: the recency-weighted 21-day median is -0.4 pts vs the full-history read — little regime change.
Headline is recency-weighted (faster 9-month half-life) over 10 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
-0.8%
mean -0.8%
% positive
9%
10 events
vs baseline
-1.2 pts
base +0.4% / 58% pos
Range
-4% … +3%
25th -1.0% · 75th -0.2%
Path · max-gain
+0.9%
median MFE in window
Path · max-draw
-2.0%
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: 2000s 72010s 72020s 10
The event log
Event date
Stretch
Fwd 21d
Max gain
Max draw
2006-02-21
-3.3%
-0.7%
+1.6%
-0.7%
2006-05-15
-3.2%
-1.7%
+0.0%
-2.7%
2006-07-14
-6.3%
-0.6%
+0.4%
-1.6%
2008-01-08
-3.2%
-4.7%
+1.7%
-4.7%
2008-03-10
-3.7%
+2.1%
+3.7%
+0.0%
2008-09-08
-5.1%
-4.9%
+2.6%
-4.9%
2008-11-05
-4.7%
-1.0%
+1.9%
-2.8%
2011-12-21
-4.0%
+2.3%
+2.6%
-0.1%
2012-10-19
-3.7%
+0.1%
+1.0%
-0.3%
2014-04-04
-3.6%
+0.3%
+1.3%
-0.4%
2016-02-05
-4.2%
+0.6%
+2.3%
-0.5%
2016-04-28
-3.2%
+2.2%
+2.2%
+0.0%
2016-12-01
-3.5%
+0.6%
+1.3%
-0.0%
2018-11-12
-3.3%
+2.0%
+2.0%
-1.3%
2020-11-10
-3.1%
+3.0%
+4.0%
+0.0%
2021-03-03
-3.4%
-0.2%
+0.3%
-3.1%
2021-05-04
-3.3%
-0.8%
+0.4%
-2.0%
2022-01-07
-3.2%
-2.3%
+0.9%
-2.9%
2022-03-10
-4.1%
+0.0%
+3.6%
-2.0%
2022-05-10
-3.7%
-1.0%
+0.0%
-3.2%
2022-10-11
-3.3%
-4.2%
+0.5%
-4.4%
2022-12-22
-3.5%
+2.6%
+2.9%
-1.6%
2024-08-07
-3.3%
-0.9%
+2.7%
-0.9%
2025-03-10
-3.1%
-0.8%
+1.5%
-1.0%
Read it honestly. The recency-weighted read leans on 10 post-2021 events (half-life 9mo); the full-history column carries 25. The regime delta shows how far recent behaviour has drifted from the long base rate. De-clustered by a 42-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.