Recommendations
0 to acquire · 2 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 |
|---|---|---|---|---|---|---|---|---|---|
| ASML | ASML Holding NV | 1575.15 | SELL ALL | 1575.15 | 1622.58⚠ | 1588.41 (+0.8%) | 1619.34 (+2.8%) | 1373.90 (-12.8%) | ASML closed decisively below its stop at the session low. The model now carries a bearish signal and projects about 13% downside over twelve weeks, so we exit the whole position. Monday's AI-slowdown sell-off hit ASML harder than the chip sector, and the valuation offers no cushion. The order book is intact, so any re-entry needs a fresh buy signal. OPERATIONAL: L origination - close 1575.15 vs stop 1622.58 (-2.92%, -0.73 ATR, bottom 6% of day range) + Target_12Week 1373.90 (-12.78%); R second leg = engine RallySell_BearTrend AVOID cv48 'do not add'. V1 escalation 30%->100% (basis strengthened NT->NT->stop break). ASML -7.25% vs mandate median -6.23% (not beta). G suppresses valuation amplify (DCF 839 broken anchor). Realized ~- (-13.78%) vs cost 1826.98. S: a gap up does not cancel. 1wk/4wk built on bearish-row Target_Price 1619.34 (above close) - read with caution; f=0.30. ADR-0020 -6.56% (not the basis). · news |
| NVDA | NVIDIA Corporation | 210.96 | SELL 51% | 210.96 | 205.91 | 215.06 (+1.9%) | 224.61 (+6.5%) | 216.60 (+2.7%) | NVIDIA closed below its 50-day average for the first time in this episode, after three straight closes below its trailing stop. Both de-risking steps we wrote down in advance are now due, so we sell about half the position. The business is strong, and NVIDIA held up better than peers in Monday's AI-slowdown sell-off, which is why the other half stays. OPERATIONAL: W1/Q tiers - 09-10 trigger (nd sub-221.79 close) [09-11 card voided by execution vocab] + 09-11 trigger (close < EMA50 214.95); close 210.96 < EMA50 214.79. W counterpoint weighed: -3.36% vs median -6.23% (rd best), conv - so no escalation beyond the written tiers. L not met (12wk 216.60 +2.67%; above stop). Retained, stop 205.91. NEXT TRIGGERS: settled close < 205.91 -> further 50%; close < 197.31 (engine stop) -> full exit. Realized ~-vs cost 226.80. f=0.30. ADR-0020: live 205.91 vs peak 221.79 = -7.16% (inside 15%). · news |
| TSM | Taiwan Semiconductor Manufacturing | 418.01 | HOLD | 418.01 | 415.38 | 424.78 (+1.6%) | 440.59 (+5.4%) | 416.97 (-0.2%) | TSMC fell less than the chip sector on Monday and is still above its trailing stop, so we hold, with a written rule to exit if the stop breaks. OPERATIONAL: HOLD cv61, <20-pt collapse), above EMA100/200, -3.52% vs median -6.23%. 12wk 416.97 inside the board-wide regime (13/20 below close, V). PROFIT_ARMED phantom (Gain_ATR -1.77) discarded (U4). TRIGGER: settled close < 415.38 (414.27 from the 09-16 ex-div session,) -> full exit (T5 stub floor, = 0.13% of book). · news |
| — | ASE Technology Holding | — | NO ACTION | — | — | n/a | n/a | n/a | ASE Technology has the strongest bullish reading left on our board, but it is only a watch signal with no buy trigger, and it fails our quality screen on negative free cash flow. OPERATIONAL: WATCH cv63, no buy print; Quality_Pass FALSE; adj 63-10-10=43. Q4: needs two consecutive bullish buy prints after this tape. |
| — | Marvell Technology | — | NO ACTION | — | — | n/a | n/a | n/a | Marvell gave back its analyst-initiation pop and dropped to a watch signal, and it still fails our quality screen. OPERATIONAL: BUY cv69 -> WATCH cv61 (-7.32% on the day); Quality_Pass FALSE; adj 41. Fourth round-trip of the same pop pattern. |
| — | Advanced Micro Devices, Inc | — | NO ACTION | — | — | n/a | n/a | n/a | AMD's buy signal faded to a watch in Monday's sell-off, so there is no entry. Re-entry needs a fresh buy print above our conviction floor. OPERATIONAL: WATCH cv61; adj 61-10 (USC-) = 51; note B suppresses val_adj. Re-arm: a BUY print with raw cv >= 75 (clears the -10 floor). |
Outcome & track record
Accuracy at the time of this record.
48 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 →
-0.226 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.