Daily Forecast 2026-09-24

All sections

📋 Morning Board 📏 Range Forecast Γ Gamma Map 🕰 Analog Days 📅 Calendar 🎯 9:00 Forecast ✅ Scorecard 🌡 Sentiment 🧭 Macro Score

📋Morning Board

Symbol	Prev close	Change	VIX / VXN (pct)	GEX ($B/1%)	Expected range
QQQ	$741.21	-0.84%	20.2 (14th pctile)	-3.66B flip 742.2	—
SPY	$767.81	-0.72%	14.2 (2nd pctile)	-5.09B flip 767.8	—

QQQ RSI(2)59 neutral

QQQ vs 200-day+11.6%

QQQ GammaDealers short gamma ($-3.66B per 1% move), flip 742.2 sits -1% above spot

How to read this · VIX

σ Volatility Indices (VIX / VXN)

VIX = S&P 500 30-day implied volatility (maps to SPY); VXN = the same measure for the Nasdaq 100 (maps to QQQ). Percentile = share of the past year (252 trading days) that closed below the current value.

Index	Current	Percentile	1-year range	As of
VIX · SPY	14.21	2% pctile · Depressed (complacency)	13.5 ─ median 17.2 ─ 31.1	2026-09-22
VXN · QQQ	20.18	14% pctile · Depressed (complacency)	17.2 ─ median 23.3 ─ 33.5	2026-09-22

CBOE official daily closes (VIX from 1990, VXN from 2009). These are closing values, not intraday — the morning brief uses the prior session's close and the evening review the current close, so the series stays consistent with history with no point-in-time bias.

📏Range Forecast

📉 今日震幅预估 —— 取数失败

脚本无有效输出（退出码 0）：9130381576, "vix": NaN, "vs_avg": NaN}, "QQQ": {"pred": NaN, "pred_adj": NaN, "tier": "中", "lo": NaN, "hi": NaN, "r2_in": 0.5222246339622105, "r2_oos": 0.484544731003973, "n": 2525, "asof": "2026-09-23", "amp20": 1.0073761379725463, "vix": NaN, "vs_avg": NaN}}
本板块本次无数据。这是故障提示，不是「今天没有预估」 —— 请检查 tools/amp_forecast.py 与 IB Gateway 状态。

ΓGamma Map

Symbol	Spot	Net GEX ($B per 1%)	Regime	Zero-gamma flip	Call wall	Put wall	Pin
QQQ	$739.41	+0.01B	Dealers long gamma	$739.39 (spot above)	$745 +0.76% · OI 11,725	$736 -0.46% · OI 22,084	$736
SPY	$765.91	-1.64B	Dealers short gamma	$767.50 (spot below)	$772 +0.79% · OI 28,410	$760 -0.77% · OI 30,041	—

Positive gamma: dealers sell rallies and buy dips, damping moves. Negative gamma: dealers chase, amplifying moves.

Walls are gamma-weighted, not raw OI. 503-day test: a NEAR call wall is real resistance and breakouts through it run shorter; a FAR call wall breaks more often (a volatility tell). Put walls show no measurable support.

DTE≤7 · Walls use the front expiry · post-close snapshot

🕰Analog Days

Prior close profile (2026-09-23, QQQ $741.21): session -0.84% · 5-day +5.18% · vs 200-DMA +11.6% · below 52-week high -0.8% · RSI2=59 · VIX 14.2 · policy rate 3.63% (1-year -0.46)

Closest analog 2025-02-20 (distance 0.43): session -0.42% · 5-day +1.69% · vs 200-DMA +9.8% · below 52-week high -0.4% · RSI2=34 · VIX 15.7 · policy rate 4.33% (1-year -1.00)
What followed: next day -2.08% · 5-day -6.88% · 20-day -10.79%

Side by side | 2026-09-23 (prior session) -0.84% ↔ 2025-02-20 -0.42%; today maps to the day after 2025-02-20, which was -2.08% (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
2025-02-20	0.43	-0.42%	-2.08%	-6.88%	34	-10.79%
2025-08-15	0.43	-0.44%	-0.04%	-0.93%	30	+2.48%
2025-07-01	0.43	-0.84%	+0.70%	+1.69%	41	+3.84%
2025-12-04	0.46	-0.09%	+0.41%	+0.42%	75	-0.79%
2025-06-11	0.46	-0.34%	+0.23%	-0.64%	57	+4.09%

Top-20 analog statistics (deduplicated — far more reliable than any single day):
Next day mean +0.02% (up 50% of the time, range -2.1% to +1%) · 5-day -0.50% (50%) · 20-day +0.23% (60%)
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 1999-03-22–2026-09-23 (6920 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”.

📅Calendar

This week (September 24, 2026 to September 29, 2026, ET time), the important US economic data releases and Federal Reserve event calendar are as follows:

09-24 Thu ET time
* [Fed Chair Speech] 09-24 Thu ET time — John Williams, the Fed's "No. 3 figure" and president of the Federal Reserve Bank of New York, stated that another rate hike may be needed this year to curb inflation, and believes that another rate hike before the end of the year is reasonable. The market's probability of a rate hike in October has approached 70%.

09-29 Tue ET time
* [JOLTS Job Openings] 09-29 Tue ET time 10:00 — Measures the situation of job vacancies in the labor market, reflecting labor demand.

09-30 Wed ET time

🎯9:00 Forecast

9:00 premarket price$734.10 (vs prior close -0.95%, Prev close $741.17)

LeanLEAN

P(close above 9:00 price)57%

Expected close$734.6

Expected high—

Expected low—

Expected range—

Gategap_down_fade

Features used5 (Missing inputs: oi|amp_failed)

Model versionv0.3-gates · 2026-09-24 09:03:50 ET

Posted at 09:05 ET, scored at 16:45 ET. The ledger keeps every call — misses included.

✅Scorecard

Called	Actual
P(up) 57% · close $734.6 · range $null–$null	Open $735.29 · High $742.66 · Low $734.62 · Close $741.10 (Close vs 9:00 price +0.95%)

Direction✓ hit

Range inside band—

Expected high touched—

Expected low touched—

Brier0.188 Brier (naive) 0.196

Close error0.89% Naive error 0.95%

Running tally · 40 calls scored · direction hit rate 18/40 · avg Brier vs naive 0.259 / 0.259

Naive baseline = "close equals 9:00 price, always 55% up".

🌡Sentiment

AAII Retail Sentiment Survey · week of 2026-09-23

Bull−bear spread -15.4 bulls 32.7% / bears 48.1%

39-year percentile 11.8% · 5-year percentile 26.2% (the distribution has shifted down; use the 5-year figure)

Historically a contrarian indicator, and it takes 3–4 weeks to work, not 1–2. Since 2020 the effect has broken down and at times inverted — low-weight atmosphere only.

CNN Fear & Greed Index · live

36.1 fear

prior close 34.7 · one week ago 28.3 · one month ago 55
Percentile since 2022 27.2%

Backtested: no predictive power for same-day or next-day direction (its components are that day's price action, which makes it circular). Forward absolute returns are positive from every bucket; only the magnitude differs — pure atmosphere.

CBOE Equity Put/Call · 2026-09-23

0.46 index P/C 1.04 · total P/C 0.86

Percentile since 2023 3% (median over the same period 0.59)
Low = retail crowding into calls (speculative heat); high = heavy put demand (defensive)

Backtested: an extremely low P/C (call mania) does not mark tops — forward returns are in fact slightly positive, the opposite of the popular claim. Atmosphere only.

All four have been backtested: none carries tradable predictive power for same-day or next-day direction. They describe the sentiment backdrop and are not a basis for buying or selling.

🧭Macro Score

Total 68 / 100 · Posture: Neutral (2026-09-24)

Category	Value	Score	Note
Macro		18 / 20
└ GDP growth (ann.)	1.5	3 / 5
└ Core CPI YoY	2.4	5 / 5
└ Unemployment	4.1	5 / 5
└ PMI (mfg+svc avg)	55	5 / 5
Monetary policy		12 / 25
└ Real rate (FFR − core CPI)	1.6	5 / 8	neutral zone 0–1.5%
└ Policy stance & guidance	model judgment	3 / 10	model judgment
└ Communication vs market	model judgment	4 / 7	model judgment
Earnings		17 / 20
└ EPS growth YoY %	51	5 / 5
└ Forward P/E	19.1	5 / 8	10-yr avg ≈ 17–18
└ Earnings quality	model judgment	4 / 4	model judgment
└ EPS beat rate %	86	3 / 3
Liquidity		9 / 10
└ IG credit spread OAS %	0.77	4 / 4
└ M2 YoY %	5.66	3 / 3	overheating also penalised
└ Financial conditions	—	2 / 3	proxied by spreads + M2
Policy & geopolitics		3 / 15
└ Domestic policy risk	model judgment	1.5 / 7.5	model judgment
└ Geopolitical risk	model judgment	1.5 / 7.5	model judgment
Sentiment & technicals		9 / 10
└ VIX regime	14.21	4 / 4	low = seller regime, high = oversold signals active; not directional
└ Trend (200-day, SPY+QQQ)	2	3 / 3	the only trend state that passed FDR
└ Flows / rotation / volume	model judgment	2 / 3	volume ratio + rotation dispersion + breadth; conditions, not direction

Weeks-to-months backdrop, not an overnight signal. Being forward-tested; it does not drive any order.

Full report: Morning report · Evening report

Research output, not investment advice.