Recommendations
1 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 |
|---|---|---|---|---|---|---|---|---|---|
| PLTR | Palantir Technologies Inc. | 191.79 | ADD — QUEUED @188.64 | 188.64 | 178.27 | 198.95 (+5.5%) | 223.00 (+18.2%) | 254.52 (+34.9%) | Palantir broke out to a fresh 20-day high as the model's top-ranked buy, and Rosenblatt reiterated its Buy rating and target on the FAA's AI airspace rollout. The stock is richly valued and closed above the model's trigger, so we add a half-size position only on a pullback to the breakout level. OPERATIONAL: STRONG BUY - ADD 80 (fresh; HOLD prior), Buy_Rank 1; val_adj -10 (MoS -14.36) + bias 0 (BreakoutUp_20D|buy n=1 report-only) = adj 70 >= 65. No-chase: ED -0.47 with close 191.79 near the 193.79 high, so the printed buy-stop @188.64 would fill as a chase (L1/UT-6/V7); ASSUMPTION: queued as a GTC LIMIT at the printed Entry_Price. Volume 112.34% x = 434.76 x 0.5 (MoS <= -3) =; max_position 60% and do not bind. RSI_DIV on the row: unarmed (Gain_ATR 2.36), G1/G2/G3 bar any trim; the 0.5x modulator covers it. U2 passes (12wk 1.35x entry). Stop 178.27 = Y5 2.0xATR chandelier, whole position. U6: Target_Price 223 above the Est band top 203.74 - band top is the credible 4wk objective. 12wk exceeds DCF 46.62. Withdraw if conviction < 65 or the label leaves BUY/STRONG BUY; expires 2026-09-28. · news |
| SNDK | Sandisk Corporation | 1816.57 | HOLD | 1816.57 | 1589.90 | 1884.57 (+3.7%) | 2043.24 (+12.5%) | 2311.40 (+27.2%) | SanDisk's anticipation order filled at and the stock slipped 1.6% as the whole memory group sold off, but there is no sell signal and the long-term view is still well above the price. We hold and tighten the stop. OPERATIONAL: filled @1846.17 (txn ustech-20260924-0001). ANTIC 88 -> WATCH 61 (-27) is inert: unarmed, Gain_ATR -0.26 (Y6). Stop 1495.87 -> 1589.90 (Y5 2.0xATR chandelier; scan 1759.90 is 0.5 ATR, rejected per V5). Scan prints Held N (Y4 lag) - JSON governs. MU FQ4 09-30 read-through. Exit on close < 1589.90 with 12wk < close. · news |
| DELL | Dell Technologies Inc | 549.83 | HOLD | 549.83 | 517.26 | 568.26 (+3.4%) | 611.23 (+11.2%) | 783.51 (+42.5%) | Dell steadied after Tuesday's drop and the model keeps a hold with a strong long-term view, so we keep the post-trim position on its trailing stop. OPERATIONAL: BUY - ADD 71 -> HOLD 61, confirming the 09-23 no-add (UT-10). Stop 517.26 held (chandelier 488.43 looser; scan 534.48 is 0.5 ATR, rejected). Not armed (Gain_ATR 2.34 < 3; T12 70.18 floor, Z2). |
| MU | Micron Technology, Inc. | 1071.88 | HOLD | 1071.88 | 998.56 | 1100.25 (+2.6%) | 1166.46 (+8.8%) | 1316.02 (+22.8%) | Micron dipped with the memory group, but the model's caution label cleared back to a hold, and fiscal Q4 earnings on Sept 30 are inside the catalyst window, so we hold through the print with no adds. OPERATIONAL: AVOID 65 -> HOLD 68. Catalyst-aware hold (FQ4 AMC 09-30, <=5 sessions); no pre-trim, no add (L6/T3). Stop 998.56 held (chandelier 977.30 looser). · news |
| CRM | SalesForce Inc | 237.58 | HOLD | 237.58 | 238.25⚠ | 242.33 (+2.0%) | 253.40 (+6.7%) | 326.71 (+37.5%) | Salesforce bounced 1.8% and the model's conviction recovered, leaving the stock only fractionally under our alert line with a strongly positive long-term view, so we hold on the written exit rule. OPERATIONAL: alert 238.25 breached by 0.28% (was 2.09%); conv. Z3 hard exit: close < 228.98 OR (close < 238.25 AND 12wk < close) -> SELL market; 12wk 326.71 so not hit. ADR-0020: 5.4% below the 251.77 peak, cut 09- - clear. · news |
| AAPL | Apple | 337.02 | HOLD | 337.02 | 326.25 | 341.00 (+1.2%) | 350.30 (+3.9%) | 375.52 (+11.4%) | Apple's one-day no-trade reading reverted to a hold, so there is no deterioration to act on; we keep the stop. OPERATIONAL: NT 0 -> HOLD 56, so tick (d) cannot build. Unarmed (T12 89.75 < 90, Gain_ATR 0.89, no PROFIT_ARMED print). Stop 326.25 held (chandelier 323.74 looser; scan 333.70 is 0.5 ATR). |
| TSM | Taiwan Semiconductor Manufacturing C | 446.57 | HOLD | 446.57 | 431.52 | 452.58 (+1.3%) | 466.60 (+4.5%) | 476.86 (+6.8%) | TSMC eased and the model's conviction slipped, but the gain is now too small to count as a profit-take setup, so we hold on the existing stop. OPERATIONAL: PROFIT_ARMED print but Gain_ATR 0.85 < 1.0 (X2 immaterial). Conv (-19, one short of tick b). 12wk 476.86 > 1.02x close. Stop 431.52 held. Next: Gain_ATR >= 1.0 + any tick -> trim 30% (19). |
| NVDA | NVIDIA Corporation | 225.51 | HOLD | 225.51 | 218.10 | 228.69 (+1.4%) | 236.10 (+4.7%) | 240.81 (+6.8%) | Nvidia slipped just below our cost and the model's conviction faded, but there is no sell signal, so we hold on the stop. OPERATIONAL: PROFIT_ARMED prints on Gain_ATR -0.24 = arm-on-loss (UT-9), inert. Conv. Stop 218.10 held (chandelier 214.92 looser). Close < 218.10 with 12wk < close -> exit 48. |
| MSFT | Microsoft Corp | 500.59 | NO ACTION | 500.59 | 494.87 | 507.45 (+1.4%) | 523.45 (+4.6%) | 578.12 (+15.5%) | Microsoft printed a buy with an analyst upgrade behind it (Stifel to Buy, target), but it fails the book's quality screen for new positions, so it is recorded only as a not-taken idea. OPERATIONAL: BUY 75, Buy_Rank 2; val_adj -9 + bias +3 (FailedBreakdown_Up_20D|buy, Z5 passes) = adj 69; Quality_Pass False blocks new entries. Counterfactual only. · news |
| NET | Cloudflare, Inc. | 352.33 | BUY-STOP | 354.41 | 295.73 | 389.62 (+9.9%) | 471.76 (+33.1%) | 493.12 (+39.1%) | Cloudflare qualified for the early-entry slot, but it fails the quality screen for new positions, so it is recorded only as a not-taken idea. OPERATIONAL: BUY - ANTICIPATE 70 in (09-23, 09-24); Quality_Pass False. Counterfactual only. |
| SNOW | Snowflake Inc. | 334.81 | NO ACTION | 335.61 | 320.85 | 342.20 (+2.0%) | 357.56 (+6.5%) | 422.42 (+25.9%) | Snowflake printed a pullback buy, but conviction is below the book's bar after valuation and it fails the quality screen, so it is recorded only as a not-taken idea. OPERATIONAL: BUY 64 -> adj 54 < 65; Quality_Pass False. |
Outcome & track record
Accuracy at the time of this record.
43 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.