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 18 Sept 2026, 16:00:00 GMT-4

US Semiconductors — End-of-Day Verdict

EOD 2026-09-21

Recommendations

1 to acquire · 1 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
AMDAdvanced Micro Devices, Inc615.52BUY — QUEUED @566.28566.28449.83636.16 (+12.3%)799.20 (+41.1%)781.59 (+38.0%)AMD broke out to a record high (briefly a trillion company) on a reported 10% AI-chip price increase and a server-CPU rally, and printed our strongest buy signal (STRONG BUY, conviction 90) for the second time in three sessions. It closed 1.6 ATR above the model entry, so it is queued at that entry instead of chased. OPERATIONAL: new card (BreakoutUp_52W, Buy_Rank 1); Q4 passes (SB90 / ANT78 / SB90). The engine's 'Buy Stop @566.28' sits BELOW market (= a market order = a chase), so a gtc_limit at the live Entry_Price is used (8.0% below the 615.52 close; Entry_Distance_ATR -1.59, RSI 72.96 < 75). Range 558.53-574.03. Size: model 0.9534 x x 0.20 x 0.5 (MoS <= -) = =, capped by S at 1% of book / 116.45 risk/sh = =, defined risk (1.00%). Stop 449.83 (3.76 ATR wide; S binding). R:R 2.00:1 (V4); 12wk 781.59 > entry (S7). val_adj 0 per P (DCF 171.74 broken); BreakoutUp_52W|buy n=1 report-only; L1 caveat: 52W 4wk targets overshoot. R: one catalyst (Meta MUSE server-CPU rally / price-hike report) also lifted ARM/INTC/QCOM, and AMD is the only admissible member. f=0.30 (8 graded buys < 10). Withdraw: cv < 65, label leaves the bullish family, settled close < EMA20 ~513.35, or expiry after the 09-24 close. · news
ASMLASML Holding NV1711.32SELL ALL1711.321608.17n/an/a1501.81 (-12.2%)After five sessions of no signal, the model now issues an explicit STRONG SELL on ASML. The stock lagged a strong chip rally, sits 6% below cost, and projects 12% lower over twelve weeks, so we exit the small position. OPERATIONAL: late-flipped STRONG SELL - REDUCE cv69 (NT cv0 x5 -> SSR). This is R's second independent leg beyond NoTrade: an explicit labelled REDUCE plus a negative 12wk (1,501.81, -12.24%). R2: the engine tier of 77.89% = 5 of would leave a 1-sh stub, so T5 escalates to a full exit (the engine rationale itself says 'target full exit'). The valuation amplify (MoS -4.14) is suppressed by G2 (DCF 827 broken) and non-deciding. W2: +1.87% vs a +3.54% median. Market at the 09-22 open; reprice if the open gaps > ~1.5%. Proceeds, realized -. U8: the row prints no Target_Price, so 1wk/4wk are n/a. FailedBreakout_Down_20D|sell n= report-only. · news
NVDANVIDIA Corporation227.38HOLD227.38215.66230.90 (+1.5%)239.10 (+5.2%)237.43 (+4.4%)Nvidia's signal firmed to conviction 75 and the position is back above cost, so we hold it and raise the stop to the model's own level. OPERATIONAL: trail-raise 211.10 -> 215.66 (engine Stop_Price, 2.00 ATR clearance, U2 pass; ~EMA50 215.61). PROFIT_ARMED at +0.26% / Gain_ATR 0.10 comes from the T12 ratio (U4). No fire tick: no other Exit_Warning, cv is up, 12wk 237.43 > 1.02 x close, no NO TRADE. So this is a trail-raise, not a trim. Triggers: settled close < 215.66 -> sell 30%; settled close < EMA200 ~202.56 -> full exit. peak_stop stays 221.79 (erosion 2.76%, well short of ADR-0020's 15%). W2: +2.30% vs a +3.54% median, still lagging.
TSMTaiwan Semiconductor Manufacturing C445.14HOLD445.14425.52462.96 (+4.0%)504.55 (+13.3%)457.43 (+2.8%)TSMC shows its strongest reading in this book's record (conviction 93, a pre-breakout setup), so the small position is held and the stop raised. OPERATIONAL: RSI_DIV + PROFIT_ARMED (+1.63%, Gain_ATR 0.72, armed by the T12 ratio, U4). Tick (a) RSI_DIV is downgraded to a trail-raise by G1 re-scoped to a property test (U7: cv93, Trend Bullish, 12wk alive). T5: a-sh stub is never sliced. Stop 415.50 -> 425.52 (engine line, 1.99 ATR, U2 pass); new peak_stop 425.52. Trigger: settled close < 425.52 -> full exit of.
—Micron Technology, Inc.—NO ACTION——n/an/an/aMicron printed its second straight bullish signal, but tonight's is a pre-breakout (anticipation) setup, and that slot needs two such prints in the last three sessions. OPERATIONAL: BUY - ANTICIPATE cv83 = anticipate slot (not in the ACQUIRE pool); the 09-18 re-arm asked for BUY/SB, which was not printed. val_adj - (usable DCF, P). R:R 2.00:1. Re-arm (S4): 09-22 EOD prints ANTICIPATE again with cv >= 55 -> QUEUED-ANTICIPATE gtc_stop at that row's Entry_Price, 0.5x size, S-checked, expires_on no later than 09-29 (S5: FQ4 AMC 09-30).
—Lumentum Holdings—NO ACTION——n/an/an/aLumentum has a buy signal but fails our financial-quality screen, which blocks new positions. OPERATIONAL: Quality_Pass FALSE hard gate. adj 66 = 76 + 0 (broken DCF) - 10 (FailedBreakdown_Up_20D|buy; scorer now -10 = USC-).
—Sandisk Corporation—NO ACTION——n/an/an/aSandisk fell on a strong up day and its signal dropped from a pre-breakout setup to a weaker buy well below our bar. OPERATIONAL: the 09-18 anticipate re-arm did NOT fire (label BUY FailedBreakdown, not ANTICIPATE). adj 53 = 68 - 5 - 10, below the floor. W2: -1.41% vs a +3.54% median.

Outcome & track record

Accuracy at the time of this record.

57 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 →
0.091 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.