This website is for educational purposes only and does not constitute investment advice. Always do your own research and assess your own risk tolerance before making investment decisions.

US End-of-Day Verdict 30 Sept 2026, 16:00:00 GMT-4

US Semiconductors — End-of-Day Verdict

EOD 2026-10-01

Recommendations

1 to acquire · 0 to dispose

TickerNameCloseActionAction Price Where to act — a buy-limit on a pullback or a buy-stop above resistance, not the current price. Sanity-check vs Close: on a held name, an action price stranded above the close means the queued level was set when the stock was higher — stale, awaiting reprice. Stop The risk-defined exit, set below the entry for a long (~1.2–1.8×ATR). A held long whose Stop sits at/above the Close is already below its stop — a stale box awaiting reprice. 1wk Model estimate of the likely price at this horizon — a forward projection, not a guarantee, and separate from the trade's Action Price or Stop. Where the ML estimator is enabled these are per-ticker calibrated forecasts (~80% coverage band) that are refreshed periodically and can drift between refreshes; otherwise they're interpolated from the signal's swing target. Confirm against the settled close. 4wk Model estimate of the likely price at this horizon — a forward projection, not a guarantee, and separate from the trade's Action Price or Stop. Where the ML estimator is enabled these are per-ticker calibrated forecasts (~80% coverage band) that are refreshed periodically and can drift between refreshes; otherwise they're interpolated from the signal's swing target. Confirm against the settled close. 12wk Model estimate of the likely price at this horizon — a forward projection, not a guarantee, and separate from the trade's Action Price or Stop. Where the ML estimator is enabled these are per-ticker calibrated forecasts (~80% coverage band) that are refreshed periodically and can drift between refreshes; otherwise they're interpolated from the signal's swing target. Confirm against the settled close. Rationale
SNDKSandisk Corporation1787.69BUY1787.691708.001838.95 (+2.9%)1958.55 (+9.6%)2178.89 (+21.9%)Sandisk's buy signal strengthened from BUY 66 to STRONG BUY 86 on Micron's beat-and-raise read-through, it is the book's #1 quality name and its only fair-value bargain, and it trades ~24% below its 52-week high with Street consensus at Strong Buy. adj 86 -7 (MoS -1.42) -7 (FailedBreakdown_Up_20D|buy) = 72 >= 65 (69 even at USC-'s -10 floor). Q4 satisfied (B66 -> SB86, 2 consecutive bullish prints); 09-30 S4 re-arm fired as written; USC- full size allowed because Quality_Pass True (F8, QR 1). Not extended (Entry_Distance 0.00 ATR). Sizing 0.9534 x x 0.20 x 0.75 = ->; S risk (0.63%) < 1%. L8: day limit at the next open; cancel if the open gaps > ~1.5% above 1,787.69 or the label leaves the bullish family by the settled open. · news
TSMTaiwan Semiconductor Manufacturing C459.20NO ACTION459.24450.78n/an/a514.96 (+12.1%)TSMC printed STRONG SELL - REDUCE on an upper-band mean-reversion signal, but it is the fourth label flip in four sessions (H77 -> AV53 -> H70 -> SSR66), price rose +0.66%, the 12-week view is +12% and no news supports a sell, so the exit is armed rather than taken. W1 first-instance-arms: the state's written trigger needed a bearish print PLUS a second tick and only one leg is present (conv -4, not armed: T12 89.17%, Gain_ATR 2.29). Conversion: a second consecutive SELL/STRONG SELL - REDUCE or AVOID print, or a settled close < 450.78 (engine stop) -> mandatory FULL exit at the next open (T5 stub,). Ledgered optional so the counterfactual grader prices not selling at 459.20. · news
NVDANVIDIA Corporation230.86HOLD230.86220.43233.99 (+1.4%)241.29 (+4.5%)251.34 (+8.9%)NVIDIA's hold signal strengthened to 85 (from 75) as chips led a rebound and Micron's HBM guide confirmed AI demand; RSI_DIV + PROFIT_ARMED is a phantom arm (U4: +1.79%, Gain_ATR 0.78, armed on T12 ratio 91.85%), and MoS -2.03 is not < -3, so no trim. Trail raised 218.10 -> 220.43 (engine). W1: settled close < 220.43 -> sell 30%; settled close < EMA200 204.37 -> full exit. · news
ASMLASML Holding NV1808.49HOLD1808.491721.631834.55 (+1.4%)1895.35 (+4.8%)1885.38 (+4.3%)ASML holds on a softer HOLD 61 (from 73) while flat (-0.18%); PROFIT_ARMED is phantom (U4: underwater -1.01%), conviction drop -12 < 20, no early Exit_Warning code, so nothing originates a sell. Trail raised 1,718.57 -> 1,721.63 (engine). W1: any SELL/STRONG SELL - REDUCE print or settled close < 1,721.63 -> full exit. Q results 10-14.
—Lumentum Holdings—NO ACTION——n/an/an/aLumentum printed STRONG BUY 90 on a +7.67% 52-week breakout, but it fails the quality gate (F-Score 5, Quality_Rank 14/20), which blocks new entries; the stop at 769.54 is 3.76 ATR / -26% (S fails independently). W: sixth blocked bullish print. No re-arm while Quality_Pass is False.
—Micron Technology, Inc.—NO ACTION——n/an/an/aMicron beat FQ4 and guided FQ1 to -63B vs consensus, and the model now prints BUY - ANTICIPATE 96, but that is 1 of the last snapshots (needs 2) so the anticipate slot is not yet eligible. S4 re-arm: a second BUY - ANTICIPATE at the 10-02 close with cv >= 55 -> QUEUED-ANTICIPATE gtc buy-stop at THAT row's Entry_Price (never 1,113.26), 0.5x x 0.75 (MoS -1.54), S-checked, expires sessions; a BUY/STRONG BUY row at the 10-02 close instead is the 2nd consecutive post-earnings bullish print (ACQUIRE pool, adj must clear 65).
—Coherent Corp.—NO ACTION——n/an/an/aCoherent jumped +10.9% to BUY 77 straight from NO TRADE: a single-print chase that fails the quality gate; adj 77 -10 -7 = 60 < 65 and Q4 (needs 2 consecutive bullish prints). 12wk 285.93 < close.
—Arm Holdings plc—NO ACTION——n/an/an/aArm re-flipped to BUY 66 after WATCH 54 (single print, Q4); adj 66 -10 -7 = 49 < 65. Re-arm: 2 consecutive bullish prints with adj >= 65 (needs raw >= 82).

Outcome & track record

Accuracy at the time of this record.

61 Graded decisions Past recommendations old enough to score against what actually happened (target hit / stopped out / closed). This is the evidence base — the bigger the number, the more history behind the calls. Click to inspect every one. See the decisions →
0.493 1-week calibration How much of the eventual 4-week move typically shows up in the first week (0 = almost none, 1 = most of it). Use it to read the 1-week estimates: a low number means prices drift toward the target slowly, so don't over-read a soft week-1.
91 Published records How many dated end-of-day verdicts exist for this book — the length of the public track record you can browse in the Archive below.

This website is for educational purposes only and does not constitute investment advice. Always do your own research and assess your own risk tolerance before making investment decisions.