Nasdaq-100 + the AI / humanoid complex · 146 of 147 resolved

AI & Humanoid Screen

Ranked by %B ascending — which names are on sale — not by momentum. Measured on the AI complex over the 2023+ wave, forward 60 days: buying dips beat simply holding by +3.47 pts, while buying strength lost 2.65 pts and top-quartile 12-month momentum lost 3.01 pts. Owning the complex at all was worth +17.95%, which is roughly five times what the timing overlay adds.

1. Is it on sale?%B < 0.20

%B says where price sits inside its normal trading channel. Below 0.20 means it has pulled back to the bottom of that channel — on sale. Above 1.00 is extended: too stretched to buy, and it returned 2.65 pts below simply holding.

2. Above or below the 200-day?a trade-off, not a gate

Two studies disagree, so this is not a filter the verdict column applies. 46 large caps, 15y, fwd 60d: dips above the 200-day hit 71% vs 68% below — better odds, but below-200d averaged slightly more (+7.16% vs +6.96%). The AI complex, 2023+: dips below the 200-day were the best bucket of all, +7.49 pts vs the null. The Meta trade in the box below was 11.8% below its 200-day. Above = steadier; below = bigger and lumpier. Pick per your tolerance.

3. Does it survive bad timing? 2y pos ≥ 80% AND 2y p10 > -10%

Both halves are gates, and 2y pos is often the binding one. p10 is the 10th-percentile outcome across past 2-year holds — your unlucky-but-realistic case; a −50% p10 means one in ten 2-year holds halved. These are the exact thresholds the verdict column applies, not a rule of thumb.

The exit is a rule, not a guess — but be clear which rule. Everything in these tables is a fixed hold: the +3.47 / −2.65 / +7.49 pt figures are 60 trading days, entry at the next open, and the 2y pos / 2y p10 columns are 504-day holds. Nothing on this page measures a middle-band exit.
Selling on the first close above the 20-day middle band is the rule used by the separate SOXX/SOXL/SOXS band strategy in the morning brief, and it is a reasonable discipline — it just is not what produced these numbers. Reproduce the tabulated edge by holding the horizon, not by exiting at the midband.
Why there are two signals. Meta launched Muse on 2026-09-08 and ran +20.3% before the first analyst upgrade on 09-21 — following that upgrade captured 2% of the move. Replaying these rules over those sessions:
%B < 0.20 dip rule2026-08-21 @ 549.47+35.4%18 days before the launch, and META was 11.8% below its 200-day
move + volume spike2026-09-09 @ 653.17+13.9%the day after the launch
follow the analyst2026-09-21 @ 741.25+0.4%the move was over
The dip rule caught it by accident — it was buying a drawdown, not predicting a product. The spike rule reacts to the catalyst, late but not uselessly. They are labelled separately so a reaction is never mistaken for a setup.

Semis — SOXX / SOXL / SOXS

The 3x pair moves with SOXX, so read SOXX's %B and size with SOXL/SOXS's ATR. SOXS is inverse: its %B means the opposite.

TickerClose1d%Bvs 20dvs 200drangeATR$vol/d2y pos2y p10msgsVerdict
SOXX
semis_etf		 566.07+0.06% 0.94 +8.0%+26.7%77% 3.1%4.2B 95% 4w +7.3%— neutral
SOXL
semis_etfleveraged		 146.33+0.05% 0.93 +21.9%+28.0%43% 8.6%8.1B 76% 4w -52.2%— leveraged · not rated
SOXS
semis_etfleveragedinverse		 33.63-0.09% 0.07 -24.3%-81.6%0% 13.1%2.6B 0% 4w -98.7%30 leveraged · not rated

What is moving SOXX

The ten holdings behind SOXX, their fund weight, and how much of the day each one contributed (fund weight × its move, so together they explain about 61% of the fund).

Weight above its own 20-day88%
Weight that rose today44%
Top-10 contribution today+0.32%
Largest moverINTC +0.20% · 28% of gross movement
Tiles are the nightly snapshot, as of 2026-09-24. Refresh live re-prices the rows; the tiles and the chart only update when all ten come back for the same session.
Weighted daily return of the top ten (renormalised to 100%), last 20 sessions · most recent on the right
2026-08-27 +2.31%2026-08-28 -3.32%2026-08-31 +0.55%2026-09-01 -1.78%2026-09-02 +0.63%2026-09-03 +0.30%2026-09-04 +3.96%2026-09-08 +2.31%2026-09-09 +0.55%2026-09-10 -3.31%2026-09-11 +1.13%2026-09-14 -5.27%2026-09-15 +0.10%2026-09-16 +0.87%2026-09-17 +3.65%2026-09-18 +2.96%2026-09-21 +4.81%2026-09-22 +1.96%2026-09-23 -1.34%2026-09-24 +0.53%
Last 5 sessions — return: +3.0%, +4.8%, +2.0%, -1.3%, +0.5% · weight rising: 92%, 100%, 100%, 8%, 44%
TickerFund wt1dContrib5d20dTrendvs 20d
NVDA9.43%-0.41%-0.039%+2.4%+7.2%above 20d
MU8.91%+0.81%+0.072%+10.5%+15.1%above 20d
AMD8.23%+2.38%+0.196%+15.4%+30.8%above 20d
AVGO7.48%-1.30%-0.098%+1.1%-1.3%BELOW 20d
INTC5.09%+3.91%+0.199%+17.1%+44.4%above 20d
MRVL4.66%-0.75%-0.035%+7.6%+5.6%above 20d
TSM4.65%+1.03%+0.048%+4.9%+8.3%above 20d
AMAT4.59%-0.03%-0.001%+13.6%-1.1%above 20d
LRCX4.27%-0.04%-0.002%+14.2%-1.7%above 20d
KLAC4.12%-0.40%-0.016%+10.7%+1.8%above 20d
How to use this for SOXL vs SOXS. SOXX %B 0.94 sits in the middle, where the measured edge is zero either way.

Breadth is context, not a trigger. Reproduce every number here with scripts/soxx_breadth_study.py (8 years of SOXX, entry at the next open). Broad strength has no edge: top-10 weight above its 20-day > 80% was +0.04 pts vs the null at 20 days (n=727; +0.00 at 5d, −0.03 at 1d). Weakness in the holdings (breadth < 20%, or their composite %B < 0.20) pointed the same way as SOXX's own dip signal but smaller (about +0.7 to +0.9 pts vs +1.3) and rests on a few hundred overlapping observations, so treat it as noise-level: it adds nothing you cannot read off SOXX's own %B. Use this table to see why SOXX moved, broad or one name, and take the direction call from SOXX's %B. SOXL and SOXS are daily-reset products and are not rated on this page.

Mega caps

META, GOOGL, MSFT, AAPL, AMZN, NFLX — tracked every day whether or not they signal.

TickerClose1d%Bvs 20dvs 200drangeATR$vol/d2y pos2y p10msgsVerdict
META
ndx100ai_platformmegacap		 777.59+4.50% 1.02 +19.4%+24.4%100% 3.5%10.6B 79% 4w -28.1%— extended
GOOGL
ndx100ai_platformmegacap		 342.36+1.34% 0.52 +0.1%+1.4%64% 2.6%8.7B 90% 4w -0.1%— neutral
MSFT
ndx100ai_platformmegacap		 497.93-0.53% 0.44 -0.3%+15.7%79% 2.2%11.4B 96% 4w +10.0%— neutral
AAPL
ndx100megacap		 335.92-0.33% 0.74 +2.4%+17.0%96% 2.1%13.4B 99% 4w +16.2%— neutral
AMZN
ndx100megacap		 249.38+0.04% 0.21 -2.1%+3.6%59% 2.4%8.7B 79% 4w -25.5%— neutral
NFLX
ndx100megacap		 71.72+0.50% 0.13 -7.1%-15.5%7% 3.1%2.5B 77% 4w -39.2%— DIP · FAILS HOLD

Live lookup & sizing

Any symbol, priced now. The browser cannot call Yahoo directly (no CORS), so this goes through this site's own /api/quote and then applies the same formulas as the nightly table, ported from the Python — so a live check and the tables cannot disagree. Cached 10 minutes.

Buy zone

%B below 0.2, liquid, and passes the 1–3 year hold gate (≥80% of rolling 2-year windows positive with a 10th percentile above -10%).

TickerClose1d%Bvs 20dvs 200drangeATR$vol/d2y pos2y p10msgsVerdict
PAYX
ndx100		 101.59-2.78% -0.11 -14.0%-0.9%41% 3.4%315M 88% 4w -2.3%1 BUY ZONE
XEL
ndx100		 69.56-1.56% -0.07 -5.9%-9.7%0% 1.9%392M 82% 4w -6.9%0 BUY ZONE
AEP
ndx100		 117.57-0.70% -0.04 -3.7%-6.3%39% 1.7%466M 86% 4w -2.5%0 BUY ZONE
PCAR
ndx100		 110.67-1.27% -0.03 -8.1%-7.9%42% 2.6%345M 98% 4w +8.1%1 BUY ZONE
VRSK
ndx100		 168.65-1.83% 0.11 -6.8%-11.5%14% 3.6%255M 83% 4w -9.3%— BUY ZONE
ORCL
ai_platform		 139.54-3.47% 0.11 -6.6%-15.0%13% 5.3%4.3B 98% 4w +14.6%— BUY ZONE
MNST
ndx100		 42.67-2.82% 0.13 -3.8%+1.0%59% 2.3%448M 95% 4w +3.8%— BUY ZONE
BKNG
ndx100		 157.41+0.97% 0.13 -12.3%-14.1%6% 4.2%1.1B 84% 4w -5.0%— BUY ZONE
ADP
ndx100		 263.11-0.22% 0.14 -3.8%+12.0%77% 2.2%575M 93% 4w +4.2%— BUY ZONE
CSCO
ndx100		 106.97+0.51% 0.14 -2.2%+11.0%65% 2.7%2.0B 82% 4w -3.2%— BUY ZONE
TMUS
ndx100		 165.35-0.19% 0.14 -6.3%-13.1%4% 3.2%797M 95% 4w +8.7%— BUY ZONE
CCEP
ndx100		 100.31+0.62% 0.19 -3.7%+2.5%59% 2.1%179M 94% 4w +5.4%— BUY ZONE

Catalyst spikes today

A move of 5%+ on 2×+ the 20-day average volume. This is a reaction, not a setup — something happened, and the rule does not know what or which direction it resolves.

Nothing in this group today.

Near the band / neutral

Dips that fail the hold gate, plus names with no measured edge either way.

TickerClose1d%Bvs 20dvs 200drangeATR$vol/d2y pos2y p10msgsVerdict
CDW
ndx100		 139.46-4.58% -0.06 -6.0%+6.5%66% 4.3%240M 79% 4w -30.4%0 DIP · FAILS HOLD
TTD
ndx100		 12.63-0.39% -0.01 -9.7%-46.0%0% 5.2%264M 70% 4w -46.8%30 DIP · FAILS HOLD
INTU
ndx100		 277.13-3.37% -0.01 -14.2%-31.3%5% 5.1%1.2B 84% 4w -10.3%15 DIP · FAILS HOLD
PEP
ndx100		 128.15-1.56% -0.00 -5.3%-11.7%0% 1.8%1.1B 78% 4w -11.1%4 DIP · FAILS HOLD
CSGP
ndx100		 27.86-1.42% 0.03 -8.2%-32.5%1% 4.4%183M 62% 4w -22.7%0 DIP · FAILS HOLD
MELI
ndx100		 1,754.13-2.51% 0.04 -7.1%-5.0%22% 3.4%765M 78% 4w -24.0%2 DIP · FAILS HOLD
CPRT
ndx100		 28.04-2.87% 0.05 -10.0%-17.1%5% 3.7%294M 87% 4w -16.3%0 DIP · FAILS HOLD
KHC
ndx100		 23.86+0.29% 0.09 -3.4%+2.5%50% 2.6%357M 37% 4w -58.1%2 DIP · FAILS HOLD
CMCSA
ndx100		 22.13-1.86% 0.10 -10.8%-16.2%2% 3.3%667M 57% 4w -26.9%— DIP · FAILS HOLD
KDP
ndx100		 30.88-2.77% 0.12 -2.8%+6.0%70% 2.4%354M 70% 4w -9.2%— DIP · FAILS HOLD
NFLX
ndx100megacap		 71.72+0.50% 0.13 -7.1%-15.5%7% 3.1%2.5B 77% 4w -39.2%— DIP · FAILS HOLD
TTWO
ndx100		 202.98-1.62% 0.14 -5.5%-10.1%18% 3.7%502M 76% 4w -25.0%— DIP · FAILS HOLD
ALB
humanoid_materials		 108.25-4.60% 0.15 -11.5%-30.2%21% 4.9%269M 49% 4w -62.4%— DIP · FAILS HOLD
MDLZ
ndx100		 60.86-0.94% 0.15 -1.5%+3.3%71% 2.0%477M 79% 4w -7.6%— DIP · FAILS HOLD
SBUX
ndx100		 93.65-0.52% 0.15 -6.7%-4.0%54% 2.5%657M 75% 4w -8.6%— DIP · FAILS HOLD
FANG
ndx100		 189.01+1.81% 0.16 -4.8%+3.8%71% 3.3%382M 68% 4w -49.1%— DIP · FAILS HOLD
ROP
ndx100		 364.02-0.64% 0.17 -7.4%-1.8%25% 2.8%285M 85% 4w -15.4%— DIP · FAILS HOLD
ADBE
ndx100		 238.93-0.73% 0.17 -8.9%-9.2%27% 4.1%1.2B 64% 4w -43.1%— DIP · FAILS HOLD
CSX
ndx100		 46.95-0.51% 0.21 -3.3%+7.2%69% 2.1%507M 90% 4w -0.2%— neutral
AMZN
ndx100megacap		 249.38+0.04% 0.21 -2.1%+3.6%59% 2.4%8.7B 79% 4w -25.5%— neutral
AXON
ndx100		 445.00-1.24% 0.24 -10.3%-11.2%24% 5.7%442M 98% 4w +21.6%— neutral
ODFL
ndx100		 174.93-1.57% 0.24 -4.5%-11.9%40% 3.2%311M 88% 4w -5.8%— neutral
RRX
humanoid_disclosed		 151.11-0.86% 0.26 -3.2%-19.7%21% 4.0%201M 80% 4w -7.1%— neutral
COST
ndx100		 896.48-0.91% 0.26 -1.8%-6.4%20% 1.5%1.9B 100% 4w +27.0%— neutral
BKR
ndx100		 57.29-1.28% 0.27 -4.8%-2.5%53% 3.0%446M 66% 4w -44.0%— neutral

Extended

%B above 1.00 — the stall zone, −2.65 pts vs the null at 60 days. Not a short signal; a not-today signal.

TickerClose1d%Bvs 20dvs 200drangeATR$vol/d2y pos2y p10msgsVerdict
INTC
ndx100soxx_top10		 127.39+3.91% 1.00 +23.7%+61.7%88% 5.0%10.4B 49% 4w -37.8%— extended
META
ndx100ai_platformmegacap		 777.59+4.50% 1.02 +19.4%+24.4%100% 3.5%10.6B 79% 4w -28.1%— extended
AME
humanoid_association		 247.74+0.52% 1.02 +4.3%+8.6%87% 2.1%288M 99% 4w +15.3%— extended
ROST
ndx100		 235.40+0.61% 1.05 +2.6%+9.2%82% 2.2%515M 80% 4w -7.0%— extended

Does the dip rule hold up as a quarterly rotation?

Buy the dip names at each quarter-end, hold to the next, versus the same number of names drawn at random from the same list (2000 draws), after 0.20% costs. Thresholds were written before each run. Neither variant cleared them, so nothing here changes the verdicts above. The universe is today's AI leaders, which flatters dip entries; the mean is carried by one quarter (2026-03-31) in v1.

Testsignal qtrsmean net excessqtrs positiveex best qtrp vs randomresult
v1 · dip (%B < 0.20)23+4.2 pts52%+1.0 pts0.071not promoted (failed: P1, P4)
v2 · dip + above 200-day18+3.3 pts39%-4.8 pts0.259not promoted (failed: P1, P3, P4, P5, P6)

The 1–3 year durability gate cannot be tested point-in-time on 10 years of data (needs 2016 prior sessions); it is judged forward only. Method and thresholds: docs/experiments/2026-09-24-preregistration-qr-s1-v{1,2}.md.