The 20 most similar historical sessions across 25 features, and what followed them.
Prior close profile (2026-11-06, QQQ $656.10): session +1.40% · 5-day -4.98% · vs 200-DMA -3.6% · below 52-week high -13.6% · RSI2=32 · VIX 25.6 · policy rate 3.63% (1-year -0.24)
Closest analog 2025-03-12 (distance 0.51): session +1.13% · 5-day -5.00% · vs 200-DMA -3.3% · below 52-week high -11.6% · RSI2=49 · VIX 24.2 · policy rate 4.33% (1-year -1.00)
What followed: next day -1.80% ·
5-day +0.83% ·
20-day -2.29%
Side by side | 2026-11-06 (prior session) +1.40% ↔ 2025-03-12 +1.13%; today maps to the day after 2025-03-12, which was -1.80% (single days are mostly coincidence — the Top-20 statistics below are more reliable)
| Analog (top 5) | Distance |
That day |
Next day |
5 days on |
RSI2 then |
20 days on |
| 2025-03-12 |
0.51 |
+1.13% |
-1.80% |
+0.83% |
49 |
-2.29% |
| 2024-08-06 |
0.71 |
+0.96% |
-1.08% |
+5.24% |
31 |
+4.80% |
| 2018-10-12 |
0.72 |
+2.78% |
-1.21% |
-0.75% |
60 |
-1.61% |
| 2022-01-26 |
0.72 |
-0.16% |
-1.01% |
+6.94% |
6 |
-1.18% |
| 2018-04-03 |
0.76 |
+1.13% |
+1.58% |
+2.51% |
47 |
+3.51% |
Top-20 analog statistics (deduplicated — far more reliable than any single day):
Next day mean +0.03% (up 50% of the time, range -4.5% to +3%) · 5-day +2.51% (85%) · 20-day +3.55% (80%)
Note: QQQ drifts up over time, so the unconditional probability of any given next day being positive is already about 55%. Compare the “up %” above against that baseline, not against 50%.
25 features in three equally weighted groups: price position (return / distance to moving averages / position in the 52-week range / trend slope / consecutive up-down days / gaps) + technicals (RSI2 / RSI14 / volatility / relative volume / volume trend / range / KDJ-J / Bollinger %B / MACD histogram) + environment (VIX / rate cycle / credit spreads / dollar index / oil / S&P P/E / CBOE equity P/C / AAII bull-bear spread). Weighted z-score Euclidean distance; matching pool 1999-03-22–2026-11-06 (6952 days, excluding ±60 days around the target). Narrative context, not a trading signal: after four rounds of feature engineering the Top-1 next-day directional hit rate tops out at 54.9%, still below the 57% you get by always guessing up. The data is given in full, but do not use it for direction — it answers “which historical setup does today resemble”, not “will tomorrow be up or down”.
Research output, not investment advice.