The 20 most similar historical sessions across 25 features, and what followed them.
Prior close profile (2026-08-19, QQQ $716.08): session -0.20% · 5-day -1.05% · vs 200-DMA +9.8% · below 52-week high -4.0% · RSI2=8 · VIX 14.9 · policy rate 3.63% (1-year -0.70)
Closest analog 2025-12-15 (distance 0.39): session -0.50% · 5-day -2.20% · vs 200-DMA +10.9% · below 52-week high -4.0% · RSI2=4 · VIX 16.5 · policy rate 3.64% (1-year -0.94)
What followed: next day +0.20% ·
5-day +1.42% ·
20-day +1.48%
Side by side | 2026-08-19 (prior session) -0.20% ↔ 2025-12-15 -0.50%; today maps to the day after 2025-12-15, which was +0.20% (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 |
| 2025-12-15 |
0.39 |
-0.50% |
+0.20% |
+1.42% |
4 |
+1.48% |
| 2025-08-19 |
0.46 |
-1.36% |
-0.59% |
+0.58% |
3 |
+3.64% |
| 2018-04-23 |
0.47 |
-0.25% |
-2.12% |
-0.59% |
13 |
+4.02% |
| 2026-01-02 |
0.50 |
-0.19% |
+0.79% |
+2.21% |
4 |
+2.12% |
| 2018-03-16 |
0.52 |
-0.30% |
-2.29% |
-7.31% |
17 |
-4.92% |
Top-20 analog statistics (deduplicated — far more reliable than any single day):
Next day mean -0.19% (up 60% of the time, range -2.3% to +1.3%) · 5-day -0.45% (45%) · 20-day +0.84% (75%)
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 1999-03-22–2026-08-19 (6896 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.