Recommendations
1 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 |
|---|---|---|---|---|---|---|---|---|---|
| NVDA | NVIDIA Corporation | 223.96 | BUY-STOP — QUEUED @224.39 | 224.39 | 201.51 | 238.12 (+6.1%) | 270.17 (+20.4%) | 240.02 (+7.0%) | NVIDIA re-armed its anticipation setup at the highest conviction of the run (88, up from 68) after SpaceX committed to building its data centres — on Earth and in space — exclusively on NVIDIA hardware, a demand commitment from a potential new top-five customer rather than a multiple story; the stock closed the week up more than 10% as AI-chip fears eased. Valuation is stretched against the earnings-power anchor (MoS -2.52, a -10 haircut) but quality is the second-best in the book at rank, so the entry is taken small and on a buy-stop that only fills if the market confirms the breakout. Operational: first anticipate slot ever filled in this book (slot eligibility 2-of-3 prints: 08-06 ANTICIPATE 83, 08-07 BUY 68, 08-08 ANTICIPATE 88). GTC buy-stop at the live snapshot Entry_Price, ED +0.06 = +0.19% above the 223.96 close — provenance-clean, no chase. Sizing: 0.50 x x 20% =, x0.75 size modulator (MoS in the -3..-1 band) =, x0.5 anticipate slot = -> = (3.7% of) against. 1wk uses f=0.30 per L5 (calib_1w 0.134 on <10 graded buys). 12wk 240.02 exceeds the DCF anchor 163.98 and also sits BELOW the 4wk 270.17 — forward-curve inversion, read the 4wk as the trade objective. Event risk inside the queue life: 08-11 CRWV Q2 (add-after-print, reads to NVDA, +/-10%) and 08-12 July CPI (tighten-trail) — the reason for half-size and a 3-ATR stop. AnticipationUp_VCP|buy is n=0 in this book's scorecard, so this card is the family's first data point. Auto-withdraw if conviction < 65 before fill; expires 2026-08-12. · news |
| DELL | Dell Technologies Inc | 453.77 | HOLD | 453.77 | 444.14 | n/a | 528.86 (+16.5%) | 635.29 (+40.0%) | Dell recovered +3.68% to close back above cost (+1.02%, +) as the AI-infrastructure complex bounced, and conviction rose with no exit warning and a 12-week view 40% above the close — nothing in the signal, risk, valuation or profit-take framework originates a sell, so the position is held in full. The bear case remains a margin thesis (gross margin 18% vs 21% y/y under memory-cost pressure, UBS Neutral on server demand already priced in) against a 3bn AI backlog — a watch on a held name, not a sell basis. Operational: all four origination classes tested and fail — L2 needs stop-break AND negative 12wk, and neither leg holds (price 2.17% above the carried stop, 12wk +40.0%); ADR-0020 erosion 6.27% (engine 416.30 vs peak 444.14) is under the 15% trigger and the rule is off for this book; valuation MoS -3.02 crosses the tier-bump threshold but cannot originate and G2 suppresses the amplify on a 4.3x DCF/EPV internal spread (DCF 485.61 sits ABOVE the close); ADR-0012 not armed (Gain_ATR 0.12 vs 3.0, T12_Progress 71.43 vs 90). Stop HELD at 444.14 under the monotonic ratchet, NOT lowered to the engine's 416.30 — but disclosed as only 0.26 x ATR below price on a high_vol name, so the next breach is an alert, not an exit. Real escalation level is EMA20 425.89 / engine stop 416.30 with the 12wk rolling flat-or-negative. 08-12 CPI carries a tighten-trail stance inside the window. No fresh news for the move. |
| AAOI | Applied Optoelectronics, Inc. | 135.63 | NO ACTION | 141.04 | 95.57 | n/a | 231.99 (+64.5%) | 92.60 (-34.3%) | Applied Optoelectronics printed the highest conviction score in this book's history (90) on a 20-day breakout, but the move is a post-earnings gap — Q2 revenue nearly doubled to with a swing to profit and full-year guidance above $1bn — and the model's own entry sits 4% ABOVE that gapped close, so taking it means paying up on top of a blowout print rather than buying a pullback. The position is passed: the same scan puts the 12-week view 32% BELOW the current price, and the company earns a free pass through the quality screen only because its earnings power is negative, not because its fundamentals are sound (F-Score 4, free cash flow -, quality rank). Operational: refused on L6 (no post-earnings gap chase) with UT-1 as this book's own confirmed precedent (MU +14% AH round-tripped to cv51/HOLD in two sessions). Adjusted conviction 90 cleared the 65 floor by 25 points — this is a deliberate override of the highest signal the book has produced. Corroborating: Target_12Week 92.60 vs a 135.63 close (-31.7%) against a Target_Price of 231.99 (+71%) on the same row; Est_Low 94.94 sits 30% below the close; Val_Signal NA because EPV_per_share is -, which switches the quality gate OFF by construction on the worst-quality name in the book (systemic finding 1). Would-be size 0.6695 x x 20% = -> @ 141.04, a 13.4% position. Ledgered direction:none/optional so the counterfactual grader prices what the refusal cost or saved. Re-arm on a PullbackBuy_VWAP print with the entry at or below the close, toward EMA20 115.64 — not a second breakout leg. · news |
| NET | Cloudflare, Inc. | 300.27 | NO ACTION | 309.31 | 247.13 | n/a | 433.66 (+40.2%) | 408.73 (+32.1%) | Cloudflare printed a conviction-90 momentum continuation and rose 5.6%, but the move is the reaction print to its own 08-06 Q2 results, and the book does not chase post-earnings gaps. It also fails the hard quality screen on its own merits — an F-Score of 3 and a free-cash-flow yield of 0.29% — so no new position is opened regardless of how strong the technical looks. Operational: blocked by the quality gate (Quality_Pass FALSE), independently refused by L6 (NET Q2 was 08-06, horizon stance hold-through, band +/-12%), and third-strike discounted by L1/UT-12 (MomentumContinuation_Up is 0-for-2 in this book's own scorecard). The -996 MoS is arithmetically meaningless — FV_per_share is a degenerate EPV anchor — but the gate is an F-Score/FCF screen, not the EPV, so it fires correctly and on separate evidence. Would-be size Ledgered direction:none/optional per the 07-18 advisory (iii) so the gate's cumulative cost is measurable before it is ever re-litigated. · news |
| COHR | Coherent Corp. | 379.13 | NO ACTION | 356.06 | 253.19 | n/a | 561.80 (+57.8%) | 346.71 (-2.6%) | Coherent jumped 13.4% on AI-optics demand and reported US restrictions on Chinese optical transceivers, but the book passes on three independent grounds: it fails the quality screen on deeply negative free cash flow, price has already run 6% past the model's own entry so any order today is a chase in disguise, and it reports Q4 earnings on 08-12 — two sessions after execution — with consensus EPS up 93% year on year. The move is real, which is precisely why it will still be there after the print. Operational: Quality_Pass FALSE (F-Score 7 but FCF -) blocks the new entry; Entry_Distance_ATR -0.57 means the buy-stop at 356.06 sits 6.1% BELOW the 379.13 close, so UT-6 requires it to queue as a GTC limit awaiting a 6% pullback rather than fill at market — not a conviction trade; earnings 08-12 (guided revenue midpoint 98bn) is a binary inside the queue life. Adjusted conviction 66 cleared the floor by one point. Would-be size Ledgered direction:none/optional to price the gate's cost. · 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.