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 |
|---|---|---|---|---|---|---|---|---|---|
| TSM | Taiwan Semiconductor Manufacturing C | 414.00 | SELL ALL | — | 382.61 | n/a | n/a | 376.25 | Exit the last of a losing TSMC position the model can no longer form any view on. The signal engine prints NO TRADE with conviction 0 and an Indeterminate pillar consensus ('consensus conflict + low conviction') for the third time in four sessions, while its 12-week projection of 376.25 sits 9.1% BELOW the 414.00 close — a directionless name with a negative forward view, held at a 5.5% loss. TSMC's business news is genuinely strong (Q2 revenue 2bn +36% y/y, net income +77%, Q3 guided +37%, 2026 capex raised to -64bn, a further $100bn committed to Arizona, and roughly of open-market buying by the CEO/CFO/COO since early July) — but that is a thesis argument, not a timing signal, and it does not override. If TSMC deserves owning here it deserves a fresh entry on a live buy signal with a real stop, not the remainder of a position already 61% sold. OPERATIONAL: 9th arming (07-25, 07-28, 07-29, 07-30, 07-31, 08-01, 08-04, 08-05, today). ROOT CAUSE OF THE 8 PRIOR NON-FILLS FOUND AND FIXED IN THIS CARD: every arming since 07-25 was written execution='market_on_open', which is outside paper_executor._EXEC_KINDS {market,gtc_limit,gtc_stop}; _eligibility returns None and drops the card BEFORE the skip-logging path, so it produced no output at all. The four TSM sells that did fill (07-17 to 07-22) all used execution='market'. This card uses 'market'. Basis is signal-based per CLAUDE.md s9 (sustained NO TRADE on a held position + negative 12wk, 16th session) and L2/UT-11 (an unfilled armed exit is an incomplete exit - re-fire, do not re-litigate on price action). Stop-break leg retired (close +8.20% above the 382.61 stop). PROFIT_ARMED at T12_Progress 110.03 with Gain_ATR -1.46 is the UT-9 arm-on-loss mislabel, inert, ~21st session - this is a loss-cut, not a profit-take. Valuation amplify suppressed by G2 (DCF 45.15 vs price 414.00, ~9.2x off) so val_adj forced to 0, 17th session. Proceeds at the 414.00 anchor close ref (08-05 open printed 419.32); realised ~- (-5.48% vs 438.02 cost). Est band 375.43-425.76: top only +2.84% above the exit, floor -9.32%. 08-10 TSMC monthly revenue lands two sessions after the exit, stance 'none' - not a sale into a catalyst. RE-ENTRY: BUY/STRONG BUY conv >=65 with a live Entry_Price and a Target_12Week ABOVE entry - not a price level, and not this position. · news |
| DELL | Dell Technologies Inc | 462.70 | HOLD | — | 444.14 | n/a | 536.94 | 651.80 | Hold the full 542-share Dell position and raise the stop. Yesterday's 195-share add filled at 466.595 on the open exactly as ordered, taking the book to at a blended 449.19 cost and a +3.01% gain, but the stock then printed a new 52-week high at 485.70 and reversed to close 462.70 - so the fresh add is already 0.83% under water and conviction has decayed as the 52-week-breakout label reverted to a weaker consolidation signal. Nothing here is a sell: the 12-week projection of 651.80 is still 41% above the close, there is no exit warning, and no signal-based, risk-discipline or valuation-amplified reason exists. The one thesis worth carrying is the memory-cost squeeze - Dell buys the memory whose rising price is enriching its suppliers, and gross margin has already compressed to 18% from 21% year over year - which is a margin watch item on a position that is now a quarter of the book, not a sell basis. OPERATIONAL: stop RATCHETED 390.11 -> 444.14 (engine print; monotonic-raise rule from 08-05), Peak Stop re-bases to 444.14, ADR-0020 erosion 0% and not applicable (also default-off here). CAVEAT ON THAT STOP: the raise comes from an exit-FAMILY switch (chandelier_trail -> fixed_with_time_stop), not from the trail advancing, and leaves the stop only 0.50 x ATR below the close on a high_vol name with ATR 37.12 (8.0% of price) - read a breach as an ALERT, not an automatic exit; the L2 test cannot fire anyway because the 12wk is +40.9%. Tighten with intent around 08-07 NFP and 08-12 CPI (both horizon stance tighten-trail). PROFIT-TAKE TEST: NOT armed - Gain_ATR +0.36 on the TRUE blended cost (arm is 3.0) and T12_Progress 70.99 (arm is 90). UT-7 DATA NOTE: the scan row is stale (reads 'Held ', Avg_Cost 439.41) because it was generated in the same 06:00 batch as the executor fill - / cost 449.1885 come from input/ustechportfolio.json and the true is +3.01%, not the +5.30% the CSV prints. val_adj -10 (MoS -3.10 recomputed at anchor) is recorded for completeness but does not bind a hold; DELL passes quality (F-Score 8, rank 6.5/31) and its DCF anchor is 485.61 against an EPV-branch FV of 112.78 - a 4.3x internal spread, so the haircut is an earnings-power artifact blind to the AI-server ramp. No DELL event inside the 10-day horizon window (FQ2 FY2027, guided -45bn, prints late August). · news |
| NVDA | NVIDIA Corporation | 219.22 | BUY-STOP | 215.24 | 189.86 | n/a | 265.99 (+23.6%) | 219.29 (+1.9%) | Passed on Nvidia despite the strongest anticipation setup this book has ever produced - the only meaningful gainer in the universe today (+3.43% while the momentum cohort fell 2-7%), conviction 83, trend score 94, RSI 61.6 and not overbought, and the best fundamental quality rank of any name here (3rd of 31, F-Score 6, passes the quality screen that has blocked Snowflake and Alphabet for weeks). It is refused on the anticipation slot's stability rule and nothing else: the slot requires the setup to print in at least 2 of the last 3 sessions and Nvidia has printed AVOID, AVOID, then this -. Two cautions would survive even if it armed tomorrow: the 12-week projection of 219.29 against a 219.22 close is a dead-flat forward view, and the close is already through the 215.24 buy-stop trigger, so the order would fill like a market buy and lose the 'only fills on strength' protection the slot depends on. OPERATIONAL: adj conviction 83 -10 (MoS -2.45 at anchor) +0 bias = 73, eight clear of the 65 floor; size modifier would be 0.75x. Ledgered direction:none / optional:true so the counterfactual grader prices what standing down cost. WATCH: a second BUY - ANTICIPATE print tomorrow reaches 2-of-3 and arms the slot for the first time since inception - reprice to the live Entry_Price at that point (no stale limit), and require the 12wk to lift off flat. AnticipationUp_VCP|buy is n=0 in this book's scorecard - never taken, never graded. Horizon: 08-11 CRWV Q2 (stance add-after-print) and 08-12 CPI (tighten-trail) both read through to NVDA. |
| SNOW | Snowflake Inc. | 316.84 | BUY-STOP | 322.84 | 276.89 | n/a | 414.74 (+28.5%) | 451.50 (+39.9%) | Passed on Snowflake for the eleventh consecutive session, blocked three separate ways. Its adjusted conviction of 66 would clear the 65 floor, and it was one of only three names in the book to finish green today (+0.02% against a 2-7% decline across the momentum cohort) - but the fundamental quality screen fails outright (F-Score 5, negative earnings-power value of -per share, 23rd of 31 on quality rank), which is a hard block on any NEW position; the anticipation slot needs the setup in 2 of the last 3 sessions and this is (BUY, BUY, then anticipation); and at RSI 77.1 with the price 12.4% above its volume-weighted average, buying a stop-entry 1.9% ABOVE the close is precisely the chase the no-chase rule forbids. OPERATIONAL: adj = 75 -9 (MoS -1.82 at anchor) +0 bias = 66. Ledgered direction:none / optional:true so the gate's cost keeps accruing as a counterfactual. The gate has now blocked this name through a +12.0% run over 11 sessions - the largest single open question in this book, flagged for the learnings review, NOT relaxed here. MomentumContinuation_Up|buy (its recent family) is n=2, 0-for-2 on 1wk targets and folded into L1's discount list per UT-12. |
Outcome & track record
Accuracy at the time of this record.
13 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.