Recommendations
1 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 |
|---|---|---|---|---|---|---|---|---|---|
| DELL | Dell Technologies Inc | 575.31 | SELL 30% | 575.31 | 517.26 | n/a | n/a | 819.82 (+42.5%) | Dell is up about 20% on cost and makes up 49% of the book. The model has now printed no trade signal two sessions running, one day after its S&P 100 inclusion, so we bank 30% of the position and keep the rest on a trailing stop. OPERATIONAL: ADR-0012 profit-take ARMED + FIRED. Armed = scan PROFIT_ARMED on the gain branch (Gain_ATR 3.03 >= 3.0 at today's ATR 32.16; X2 materiality 1.0 cleared 3x). Fire = tick (d), the 2nd consecutive NO TRADE ('Consensus conflict + low conviction', 09-19 + 09-22); G1 does not reach (d). Catalyst-aware hold expired: S&P 100 entry was effective 09-21. The 09-19 re-arm price (579.73) was computed at the old ATR 34.0; the scan's own arm at today's ATR governs, and AA1 (PROPOSED, inert) argued the same direction. MoS -2.74 at the anchor, above the -3 bump, so 30% stays 30% (G2 would suppress the bump anyway: 12wk 819.82 >> DCF 446.05). Realized ~+Residual 636 is managed by trail (Y6(b)): stop 517.26 held (chandelier 510.99 looser, scan blank); any AVWAP_BREAK/EMA10_BREAK on the residual -> profit_take_2 (50%); decisive close < 517.26 with Target_12Week < close -> exit per L2. · news |
| AAPL | Apple | 338.98 | SELL 30% | 338.98 | 325.59 | 351.26 (+3.6%) | 379.91 (+12.1%) | 376.29 (+11.0%) | Apple's signal cooled from STRONG BUY - ADD 88 to HOLD 68 in one session, and the price is already above the average analyst target at a rich valuation, so the trim we pre-committed on 09-19 ('armed: any tick -> trim 30%') fires. It takes back most of Monday's add at about the price paid. OPERATIONAL: ADR-0012 armed (scan PROFIT_ARMED on T12_Progress 90.08; Gain_ATR 1.16 on the true post-fill cost 331.12, above the X2 floor of 1.0; the scan's 1.77 uses a stale 326.97 cost) + tick (b): conviction = 20 pts vs the prior EOD snapshot, exactly on the >= 20 threshold. Family switched BreakoutUp_52W -> AnticipationUp_VCP, so G1 does not apply, and (b) fires regardless. MoS -3.14 would bump, but G2 suppresses it (12wk 376.29 >> DCF 237.39). Counter-case recorded: 12wk still +11%; the threshold is met at the boundary; the trim nets roughly flat against the 338.61 add (realized ~+vs avg cost). Residual 120, stop 324.93 -> 325.59 (scan, 1.97 ATR). f=0.30 (L5/V2). · news |
| AMD | Advanced Micro Devices, Inc | 615.52 | BUY — QUEUED @561.13 | 561.13 | 482.32 | 608.41 (+8.4%) | 718.74 (+28.1%) | 781.59 (+39.3%) | AMD is the book's #1-ranked STRONG BUY after a chip-led rally that briefly took it past a trillion market cap. It closed at the day's high, well above the model entry, so we queue a half-size limit at the entry instead of chasing. The valuation is very stretched, which is why the size is halved. OPERATIONAL: cv 90, val_adj -10 (MoS -13.43 recomputed at anchor, T4), bias 0 (BreakoutUp_52W|buy n=3 report-only; L1 caution: 52W 4wk targets overshoot) -> adj 80 >= 65. Quality passes. U2: 12wk 781.59 = 1.39x entry. No-chase: ED -1.75, RSI 73, close 615.52 at the 616.68 high -> QUEUE (UT-6). X4: 1.75 ATR from market (< 2 ATR), so it is a live order, not a WATCH. Volume: 66.95% x equity 1,064,362 x 20% = 142,518 x 0.5 (MoS <= -3) = 71,259 / 561.13 = 126. Stop 482.32 (scan; written to state now, Y3/V6). Expires 2026-09-24 (anchor+3 sessions). Counterfactual note (advisory, Z4/V1 caveats): no_chase_queue/queue_expiry read 'cost'. · news |
| MU | Micron Technology, Inc. | 1043.96 | HOLD | 1043.96 | 955.58 | 1124.36 (+7.7%) | 1311.96 (+25.7%) | 1186.34 (+13.6%) | Micron gained another 2.8% with conviction holding in the 80s ahead of its 09-30 results, so we hold and raise the stop. OPERATIONAL: not armed (T12 88 < 90, no PROFIT_ARMED print; Gain_ATR 1.24). Y5: stop 929.67 -> 955.58 (2.0xATR chandelier beats scan 914.25). FQ4 09-30 AMC (horizon band -12/+10%): no adds into the print (L6); catalyst-aware hold. |
| TSM | Taiwan Semiconductor Manufacturing C | 445.14 | HOLD | 445.14 | 425.52 | 462.96 (+4.0%) | 504.55 (+13.3%) | 457.43 (+2.8%) | The completion sale filled at 440.80 and TSMC closed higher, with conviction up to 93 and its 12-week view back above the price. We hold the residual and raise the stop. OPERATIONAL: PROFIT_ARMED+RSI_DIV inert, because Gain_ATR 0.72 is below the X2 floor. G2/Y7: the valuation amplify is suppressed (unit-broken ADR DCF). Z3 12wk counter re-based: 457.43 > 1.02 x 445.14, 0/4. Y5: stop 415.50 -> 425.52 (scan, 1.97 ATR). |
| PLTR | Palantir Technologies Inc. | 183.09 | HOLD | 183.09 | 176.76 | 186.87 (+2.1%) | 195.69 (+6.9%) | 232.88 (+27.2%) | Palantir rose 3.1% to 183. Hold and trail. OPERATIONAL: not armed (Gain_ATR 1.16, T12 78.6). Y5: stop 169.93 -> 176.76 (scan, 1.005 ATR, tightest eligible; chandelier 170.49). |
| NVDA | NVIDIA Corporation | 227.38 | HOLD | 227.38 | 215.66 | 230.90 (+1.5%) | 239.10 (+5.2%) | 237.43 (+4.4%) | NVIDIA rose 2.3% and conviction climbed to 75. Hold the small residual on a raised stop. OPERATIONAL: PROFIT_ARMED (T12 95.8) is immaterial because Gain_ATR 0.10 < 1.0 (X2/UT-9), so the arm is inert. Y5: stop 211.10 -> 215.66 (scan = chandelier). |
| CRM | SalesForce Inc | 236.42 | HOLD | 236.42 | 238.25⚠ | 243.12 (+2.8%) | 258.74 (+9.4%) | 332.57 (+40.7%) | The 30% Salesforce trim filled at 239.80. The residual closed just under the alert line, but not at the written hard-exit level, and its 12-week view is still positive, so we hold it. OPERATIONAL: monitor breach 236.42 vs 238.25 (0.77%, 0.22 ATR). This is the pre-registered ALERT line (U5), and it is not decisive. L2's second leg is absent (12wk +40.7%), and T1 treats a stop-break with a positive 12wk as a trail event. The written Z3 hard exit stands: a close < 228.98 OR both L2 legs -> exit the remainder at market. Conviction (deteriorating; watched). ADR-0020: peak 251.77, 5.4% off, and the position was cut 09-21 -> clear. · news |
| MSFT | Microsoft Corp | 501.61 | NO ACTION | 498.76 | 488.83 | 503.19 (+0.9%) | 513.53 (+3.0%) | 584.62 (+17.2%) | Microsoft printed a STRONG BUY on the book's favoured pullback family, but it fails the F-Score/FCF quality screen, which blocks new entries. OPERATIONAL: hard quality gate (Quality_Pass False); adj 75 would otherwise clear the floor. The signal is a fresh flip (WATCH 49 -> SB 85). Ledgered for the gate-cost counterfactual (07-18 backlog iii). |
| IREN | IREN Limited | 47.23 | NO ACTION | 47.23 | 45.81 | 48.94 (+3.6%) | 52.90 (+12.0%) | 50.18 (+6.2%) | IREN ranks #2 but fails the quality screen. OPERATIONAL: quality gate hard block; also a first bullish print after three NO TRADE sessions. |
| SNDK | Sandisk Corporation | 1766.64 | NO ACTION | 1766.64 | 1712.58 | 1831.51 (+3.7%) | 1982.88 (+12.2%) | 2068.74 (+17.1%) | Sandisk's anticipation read decayed from 96 to a plain BUY 68, and the valuation haircut leaves it under the floor. OPERATIONAL: adj 61 < 65. FailedBreakdown_Up_20D|buy +3 is not blended (Z5: sign flipped -3 -> +3 in one read). No ANTICIPATE today, so the slot is ineligible. Stop sits only 0.5 ATR below entry. |
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 →
0.138 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.
91 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.