Recommendations
0 to acquire · 0 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 |
|---|---|---|---|---|---|---|---|---|---|
| DELL | Dell Technologies Inc | 437.65 | HOLD | — | 444.14⚠ | 459.87 | 511.72 | 608.49 | Holding Dell through a sharp two-day pullback. The shares have given back 9.9% from last week's 52-week high and now sit just below our protective stop, but the reason to own them is intact: Dell's AI-server backlog is at a record and the 12-week outlook still points about 39% above today's price, so this looks like the market taking profits rather than the business turning. The genuine worry is margins, not demand - Dell assembles servers using the same memory chips whose soaring prices are enriching its suppliers, and gross margin has already compressed to 18% from 21% a year ago. That is a watch item on a position we already own, not a reason to sell it. We found no company news behind the drop and are raising vigilance rather than cutting size. OPERATIONAL: stop breach is an ALERT not an exit - close 437.65 is only -1.46% (0.175 x ATR) below the carried 444.14, exactly the false positive pre-registered on 08-06 when the exit family switched chandelier_trail -> fixed_with_time_stop and left ~0.50 ATR of room. L2 tested and FAILS (needs stop-break AND negative 12wk; 12wk is +39.0%). ADR-0020 tested: peak_stop 444.14 vs engine live print 419.13 = 5.63% erosion, under the 15% trigger, and ADR-0020 is not enabled for ustech. Profit-take not armed (Gain_ATR -0.31 underwater per UT-9, T12_Progress 71.92 vs 90). Valuation val_adj -10 is amplify-only and cannot originate (CLAUDE.md 9); G2 would suppress it anyway on the 4.3x DCF 485.61 / EPV-FV 112.78 internal spread. Stop HELD at 444.14, NOT lowered (monotonic ratchet). ESCALATION: decisive close below EMA20 422.96 / engine stop 419.13 WITH the 12wk rolling to flat-or-negative arms L2 on both legs. UT-10 live - do not add into this high-ATR reset; the 08-05 ADD at 466.595 (-6.2%) is what caused the drawdown. 08-07 NFP and 08-12 CPI both carry tighten-trail stance. 1wk uses f=0.30 (L5, calib_1w 0.134 on <10 graded buys). 12wk 608.49 exceeds the DCF anchor 485.61. |
| NVDA | NVIDIA Corporation | 218.99 | NO ACTION | 218.99 | 214.97 | 223.81 (+2.2%) | 235.07 (+7.3%) | 226.27 (+3.3%) | Passing on Nvidia today on price, not on quality. It is the highest-quality name in this book on our screens and it held perfectly flat while the day's losers fell 3-13%, but the shares already trade far above what we think the business is intrinsically worth, and our own 12-week projection only reaches about 3% above today's price - too little reward to justify committing roughly of cash. We would rather wait for a stronger setup or a better price than pay up for a thin forward view. OPERATIONAL: raw conv 68 + val_adj -10 (MoS -2.44 at the 218.99 anchor close) + bias 0 = adj 58, seven short of the 65 floor. Entry is clean (ED -0.00, at the close, no chase) and Quality_Pass TRUE at Quality_Rank 3.0/31, so neither the no-chase rule nor the quality gate is what refused it. Signal family FailedBreakdown_Up_20D is L1-discounted and 0-for-2 in this book's own scorecard. Conviction arc AVOID(76) -> AVOID(69) -> ANTICIPATE(83) -> BUY(68): the setup WEAKENED 15 pts on the session it converted to an outright BUY. Anticipate slot also refused - ANTICIPATE prints, needs; yesterday's watch item (a 2nd anticipation print) did not materialise. Would-be size: 0.5071 x x 20% = x0.75 modulator = -> @ 218.99. RE-ARM: conv >=75 (to survive the -10 haircut) with a 12wk view meaningfully above entry. 08-11 CRWV Q2 reads to NVDA (add-after-print); NVDA's own Q2 is 08-26, beyond the horizon. 12wk 226.27 exceeds the DCF anchor 163.98 - projection assumes growth beyond priced-in. 1wk uses f=0.30 (L5). · news |
| SNOW | Snowflake Inc. | 318.00 | NO ACTION | 326.35 | 279.45 | 354.49 (+8.6%) | 420.14 (+28.7%) | 453.15 (+38.9%) | Standing aside on Snowflake for a twelfth session despite genuinely good news - a $6bn five-year AWS commitment that should help margins, price targets raised to by Wells Fargo and by BTIG, and a share price holding near four-year highs while the rest of the book sold off. The block is our financial-quality screen, which the company fails on earnings quality and cash generation, and the entry would also mean buying into an overbought, extended move rather than a pullback. Good news does not substitute for a balance sheet that clears the bar, and we do not chase. Q2 results land 26 August. OPERATIONAL: blocked three ways independently. (1) Quality_Pass FALSE - F-Score 5, EPV -/sh, Quality_Rank 23/31 - hard gate on a NEW entry, 12th consecutive session. (2) raw conv 65 + val_adj -9 (MoS -1.83 at the 318.00 anchor close) = adj 56, nine short of the floor. (3) RSI 77.5, highest in the book, and the buy-stop 326.35 sits +2.6% ABOVE the close (ED +0.53) - squarely inside the no-chase rule. Family MomentumContinuation_Up is 0-for-2 here and folded into L1's discount list by UT-12. Anticipate slot also refused at. The quality gate's cumulative cost in this book is now 12 sessions - flagged for the learnings review, NOT relaxed on a verdict run. 1wk uses f=0.30 (L5). · news |
Outcome & track record
Accuracy at the time of this record.
14 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 →
0.134 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.