US Semiconductors — End-of-Day Verdict
0 ACQUIRE, 0 ANTICIPATE, 1 DISPOSE | AMD SELL (100%) @ ~469.56 at the 08-11 open - the committed 475.00 escalation FIRED on the settled close (469.56, -1.15% through the line, 0.05% off the session low) with the 12wk 460.38 BELOW the close, so L2 is satisfied on both legs for the first time; realized - (-9.01%) | ACQUIRE is a trivial NO ACTION: for the first time since standalone inception the board printed ZERO bullish actionable rows (no STRONG BUY / BUY / BUY - ADD / BUY - ANTICIPATE) with names down, median -2.71% | NVDA anticipate queue WITHDRAWN unfilled - buy-stop @224.39 missed by (high 224.137), then cv (<65) AND label reverted to WATCH; NOT repriced down, zero capital committed, non-fill saved 3.05% | TSM HOLD, TRAIL RAISED 389.22 -> 389.84, catalyst DELIVERED (July rev +44.7% YoY) and hold released
Recommendations
0 to acquire · 1 to dispose
| Ticker | Name | Close | Action | Action 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 |
|---|---|---|---|---|---|---|---|---|---|
| AMD | Advanced Micro Devices, Inc | 469.56 | SELL ALL | 469.56 | 475.00⚠ | n/a | n/a | 460.38 (-2.0%) | Selling the entire AMD position after it closed decisively below the risk line we set and re-armed four sessions running - 469.56, some 1.15% through the line and just a whisker off the session low, with the 12-week projection (460.38) now sitting below the price itself. That combination of a broken stop and a negative forward view is our defined exit basis, and the news confirms rather than rescues it: a sectorwide selloff on AI-overspending fears, a 123x trailing P/E, and a report that DeepSeek is building its own AI processor, with a Q2 beat that the market simply refused to pay for. We take a 9.01% loss at a line we chose in advance rather than an open-ended one. OPERATIONAL: L2 satisfied on both legs for the first time (prior tests failed leg 1); L3 - execute now, the line has already been tested and re-armed on 08-04/05/06/07. Valuation contributes nothing - MoS_FV -10.01 amplify SUPPRESSED under G2 (DCF anchor vs a price is a broken artifact). Scorecard bias -5 (NoTrade|sell, n=8, hit_1w 0.25) argues AGAINST and is OVERRIDDEN on three stated grounds: the exit is price-line originated not label-originated; L3 forbids further deferral; and the optional_trim counterfactual (n=4, median withheld 4wk -15.33%) shows not de-risking has been the expensive choice here. ADR-0012 ticks (c) and (d) both fire but are NOT used as the basis - the arm is the 14th consecutive FALSE arm (systemic finding #1: T12-progress 101.99% on a position 9.01% underwater, Gain_ATR -1.46); a profit-take on a loss is not a mechanism this framework has. ADR-0020 at -9.85%, below the 15% trigger - the committed-line route reached a full exit before the trail-erosion backstop was needed. Executes at the 2026-08-11 open; reprice check if the open gaps >~1.5% outside 462.5-476.6, but a gap UP through 475.00 does NOT cancel - the escalation was written against the settled close, already breached. 1wk/4wk n/a: the NoTrade row prints no Target_Price, so the f=0.30 fallback (L5, calib_1w -0.548) has no span to interpolate. 12wk 460.38 exceeds the DCF anchor - annotated, not modified. · news |
| TSM | Taiwan Semiconductor Manufacturing | 418.47 | HOLD | — | 389.84 | n/a | n/a | 395.86 | Holding the 47-share TSMC core and raising the trailing stop to 389.84. The catalyst we were holding through has now landed and it was excellent - July revenue of NT58bn, up 44.7% on the year and 5.6% on the month, running ahead of the company's own raised 40%-plus full-year target, with capital spending guided up to -64bn. What is telling is that the stock barely moved on it, closing down 0.37% on a day the sector fell a median 2.71%: the business is compounding but the market has stopped paying up for the news. That removes the protective wrapper without originating a sell - the technical is not broken, price sits 7.44% above the trail, and the 12-week view actually improved. From here the trailing stop decides it, not another narrative. OPERATIONAL: 2.0xATR chandelier off the 418.47 close = 389.84, third consecutive upward ratchet (382.61 -> 385.57 -> 389.22 -> 389.84); stops move one way only. No origination class fires: L2 fails leg 1 decisively; label is AVOID (bearish family), not SELL - REDUCE; ADR-0020 cannot apply to a trail that has only ever risen; PROFIT_ARMED is the 26th CONSECUTIVE FALSE ARM (-4.46% below cost, Gain_ATR -1.37, T12-progress 105.71% - systemic finding #1). Valuation suppressed under G2 (DCF vs). USC-5 satisfied: the ARE the defined core, 78% having been cut on 08-03. Catalyst-aware hold RELEASED, delivered. · news |
Outcome & track record
Accuracy at the time of this record.
20 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 →
-0.548 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.
53 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.