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 |
|---|---|---|---|---|---|---|---|---|---|
| NET | Cloudflare, Inc. | 310.59 | NO ACTION | 310.59 | 290.49 | 323.19 (+4.1%) | 352.60 (+13.5%) | 434.53 (+39.9%) | Cloudflare printed the cleanest buy setup this book has been offered in weeks - conviction 93, rank 1, and an entry sitting exactly at the close rather than above it, so none of the usual no-chase objections apply - and it is still passed over, because it fails the hard quality screen on an F-Score of 3 and a free-cash-flow yield of 0.29%. Monday's news makes that screen look prescient rather than merely rigid: the company announced a proposed 175bn convertible note offering due 2031, which knocked the stock 3.3% premarket before it recovered to close up 3.4%. A raise of that size is precisely the balance-sheet event a weak-quality screen exists to flag - the shakiest balance sheet in the book levering up and pre-arranging dilution into strength. Operational: Quality_Pass FALSE (Quality_Rank 26/31) blocks new entries only; the -996 MoS is arithmetically meaningless on a degenerate EPV anchor and is NOT the blocking term. Family FailedBreakdown_Up_20D is on L1's discount list (own cell n=2, hit_1w 0.5, report-only). Would-be size 0.6695 x 996,531.69 x 20% = 133,435.59, x0.5 modulator = 66,717.80 -> @ 310.59 (6.7% of); ledgered as a gate-blocked counterfactual per the 07-18 advisory (iii) so the gate's cumulative cost keeps accruing. 08-12 CPI carries a hold-through stance with NET named at +/-3%. If the quality gate is ever re-litigated, this is now the highest-conviction test case in the book's history. · news |
| DELL | Dell Technologies Inc | 457.88 | HOLD | 457.88 | 444.14 | n/a | 527.34 (+15.2%) | 645.06 (+40.9%) | Dell added 0.9% on a day when the median name in this book fell 0.8%, taking the position to its best mark since entry at +1.9% (+), and nothing in the signal, risk, valuation or profit-take framework originates a sell - so it is held in full. Mizuho reiterated Outperform and lifted its target from to on agentic-AI server demand, against a 3bn AI backlog and a stock up roughly 221% year to date; the standing bear case is UBS at Neutral arguing the doubling already prices server demand, plus an unresolved memory-cost margin squeeze (gross margin 18% vs 21% year on year). That is a watch on a held name, not a sell basis. Operational: HOLD, conviction flat at 69, no Exit_Warning, 12wk +40.9%. All four origination classes fail - signal (no REDUCE, no warning, not sustained NO TRADE); L2 (needs stop-break AND negative 12wk, neither leg holds - price is 3.09% above the carried stop); ADR-0020 (peak 444.14 vs engine 440.51 = 0.82% erosion, under the 15% trigger and not enabled for ustech); profit-take (Gain_ATR 0.25 vs a 3.0 arm, T12_Progress 70.98 vs 90 - not armed, and unlike TSM in July this position is genuinely in profit so UT-9's arm-on-loss trap is not in play). Valuation MoS -3.02 sits at the tier-bump threshold but cannot originate (CLAUDE.md 9) and G2 suppresses the amplify anyway on the 4.3x DCF/EPV spread (DCF 485.61 sits ABOVE the close vs EPV 112.78). Stop HELD at 444.14 under the monotonic ratchet; the engine's print jumped 416.30 -> 440.51, closing the disagreement from 6.27% to 0.82% in two sessions - the hand-carry was leading the engine, not fighting it. Distance is 0.396 x ATR on a 7.6%-ATR name, so the next breach is an ALERT, not an auto-exit. Escalation unchanged: a decisive close below EMA20 428.94 / engine stop 440.51 WITH the 12wk rolling flat-or-negative arms L2 on both legs; 08-12 CPI sits inside that window. · 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 →
0.494 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.