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 | 1682.30 | SELL ALL | 1682.30 | 1736.47⚠ | n/a | n/a | 1559.31 (-7.3%) | Exit the position in full. ASML closed 3.12% below its protective stop for the tenth session running and the model's twelve-week view has now collapsed to 7.31% BELOW the current price, so the shares are being held against both the risk line and the forward case. The company's July guidance raise and the start of High-NA EUV production at Intel remain genuinely good news, but that is a July thesis and it has not stopped a fourth consecutive session in which the signal engine can find no tradeable setup at all; the stock also failed its quality screen and still prices in growth far beyond its cash-flow anchor. Operational: L2 basis (decisive sub-stop close 1.26xATR through the 1,736.47 line + negative 12wk) - a trend-break exit, so the ADR-0012 "never 100% from profit-take" cap does not bind. Sixth re-fire, repriced from 1,665.14. PROFIT_ARMED on this row is a false arm (position is -7.92%; systemic finding 2). cv0 NO TRADE row prints no Target_Price so 1wk/4wk are n/a, not fabricated; f=0.30 moot. Realized - (-7.92%) on a 1,826.98 cost; proceeds. · news |
| TSM | Taiwan Semiconductor Manufacturing C | 415.50 | SELL 33% | 415.50 | 405.91 | n/a | n/a | 394.18 (-5.1%) | Take one share off a deteriorating holding and keep two. TSMC's business could hardly be doing better - July revenue up 44.7% year on year and record capital spending guided for 2026 - but the market has flatly refused to pay for it, the shares still sit well above most fair-value estimates, and the model's own twelve-week view now sits 5.13% BELOW today's price. When the forward case is dead and the signal engine has gone quiet two sessions running, the disciplined move is to bank part of the position rather than wait for the risk line to be tested. Operational: ADR-0012 profit-take, armed via T12_Progress 105.41 with ticks (c) dead 12wk (394.18 < 1.02x415.50) and (d) 2 consecutive NO TRADE -> profit_take_2 50% tier. 50% of = 1.5, rounded DOWN to 1 (never round a trim up past its tier). G2 SUPPRESSES the valuation amplify: DCF 46.22 is an ADR-ratio artifact (ADR = 5 ordinary shares), so MoS_FV -13.82 must not bump; profit-take can never reach 100% regardless. G3 satisfied (forward view negative, not cutting a winner). Ex-div on 2026-09-16 is 9 sessions out, outside the <=5-day catalyst hold. Retain, stop 405.91. Third re-fire, repriced from 414.00. Realized - (-5.14%); proceeds. USC-6: an armed deteriorating trim is a card, never prose - counterfactual optional_trim n=15 median -5.06%/-15.33% [cost]. · news |
| NVDA | NVIDIA Corporation | 224.41 | HOLD | 224.41 | 211.56 | 229.49 (+2.3%) | 241.34 (+7.5%) | 240.52 (+7.2%) | Hold the full position and leave the protective stop where it is. Nvidia rose 3.21% on a reported 9bn Hugging Face agreement - a large, named, commercial catalyst - and the model's conviction jumped from, its strongest reading in a week, with the twelve-week view intact at roughly 7% above the current price. Withdrawing the previously proposed trim was the right call and it paid within a single session; there is no case for cutting a position whose signal is strengthening. Operational: ADR-0012 armed (T12_Progress 93.30 >= 90) with ZERO fire ticks - no second Exit_Warning code, conviction ROSE 15 pts (not a >=20 collapse), 12wk 240.52 > 1.02x224.41 = 228.90 alive, label is HOLD not a second NO TRADE. Armed-without-tick = mandatory trail-raise, not a trim. The raise resolves to "already tighter": the scan's 2.0xATR chandelier computes to 207.48 and the recent swing-low close is 209.66, both BELOW the standing 211.56 ratchet, which only moves up. EMA50 212.53 is the only line above it and would leave just 1.40xATR of room on a name that closed 209.66 five sessions ago, while this position is 83.4% of equity - declined deliberately. Headroom +6.07% / 1.52xATR. Value of the 09-01 non-sale, one session in: +on the that would have been trimmed. Estimates f=0.30 (calib_1w -0.226 degenerate, L5). 12wk 240.52 exceeds the 163.98 DCF anchor - projection assumes growth beyond priced-in. · news |
| MU | Micron Technology, Inc. | 956.08 | WATCH | 956.08 | 927.16 | 981.21 (+2.6%) | 1039.85 (+8.8%) | 1016.17 (+6.3%) | Near-miss, no action - the only bullish signal on the board and it still does not clear the bar. Micron is the strongest name in the mandate: memory demand is running hot, its high-bandwidth capacity is sold out through 2026, it carries the best quality score of any candidate, and the analyst community sees substantial upside from here. What it does not have is a stable entry - the label has alternated buy/watch/buy/watch across six sessions rather than strengthening - and this book's own realised record on this particular setup family is dismal enough that a fresh full-size position cannot be justified on a one-day print. Ninth consecutive session on the shortlist without a fill. Operational: 69 raw. val_adj -6 (degree-scaled from MoS_FV -1.160, Quality_Pass True). FailedBreakdown_Up_20D|buy read at the -10 USC-3 floor - the cell has now reached n=5, which is precisely the trigger USC-3 named, and the apparent improvement is illusory (hit_1w.400 but hit_4w.000 - not one graded FailedBreakdown buy has ever reached its 4wk target). 69 - 6 - 10 = 53 vs the 65 floor; even at the mechanical -2 bias it is 61, still short. USC-3 also requires a PullbackBuy_VWAP confirmation before committing size to a chase-family entry - absent. Precedent: SNDK BUY 67 on 08-31 faded to WATCH 49 in two sessions; LITE BUY 76 twice and is now -9% from there. Overlay MU override ("add only on signal, not on narrative") honoured - a signal appeared and lost on its merits; overlay is 43 trading days stale regardless. FQ4 print 2026-09-30 (L6 - do not chase into it). Size mod 0.75x recorded for reference only. 12wk 1,016.17 exceeds the 772.94 DCF anchor. · news |
| LITE | Lumentum Holdings | 870.58 | WATCH | 870.58 | 839.46 | 907.92 (+4.3%) | 995.05 (+14.3%) | 983.19 (+12.9%) | Blocked, no action - third consecutive session of vindication. Lumentum fails the fundamental quality screen outright and carries by far the most extreme overvaluation reading in the mandate, and the shares are now roughly 9% below the levels at which this book repeatedly declined to buy them in late August. A watch-list label is not an actionable entry in any case. Operational: quality gate F blocks new entries (hard). val_adj -10 (clamped from MoS_FV -34.07 x 5). FailedBreakdown_Up_20D|buy at the -10 USC-3 floor. 61 - 10 - 10 = 41. Refused at 939.03/956.14 (08-26/08-27), now 870.58; counterfactual grader should price the refusal favourably. |
| SNDK | Sandisk Corporation | 1553.40 | WATCH | 1553.40 | 1502.74 | 1614.20 (+3.9%) | 1756.06 (+13.0%) | 1512.83 (-2.6%) | Near-miss, no action, and a second week of the no-chase rule proving itself. Sandisk printed an outright buy signal on 31 August; it was deliberately not queued, and the signal has since decayed to a watch-list reading barely half the strength of the entry threshold even though the shares themselves bounced 1.08%. Buying one-day spikes in this mandate has not worked. Operational: val_adj -6 (MoS_FV -1.106, Quality_Pass True). FailedBreakdown_Up_20D|buy at the -10 USC-3 floor. 49 - 6 - 10 = 33 vs the 65 floor. Second consecutive WATCH 49 print after the 08-31 BUY 67. |
Outcome & track record
Accuracy at the time of this record.
40 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.