US — End-of-Day Verdict
NO ACQUIRE (7th consecutive) | DISPOSE 1: NVDA -30 | GOOGL hold-at-risk 345 post-earnings settle
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 |
|---|---|---|---|---|---|---|---|---|---|
| NVDA | NVIDIA Corporation | 212.06 | SELL 30% | 212.06 | 201.00 | 212.55 (+0.2%) | 211.39 (-0.3%) | 217.81 (+2.7%) | Nvidia has reached its twelve-week objective and the model's forward view now sees the shares dead-flat from here - roughly nil at one week, slightly negative at four weeks (211.39, -0.3%) and only +2.7% at twelve weeks. That is a spent risk/reward on a large winner, so we bank a third and let seventy shares ride the intact AI-hardware trend behind a raised stop; the 07-29/30 FOMC and cloud-capex updates (Alphabet just guided capex HIGHER on +82% cloud growth) argue for staying invested in the majority. A partial de-risk, not a call against the story. OPERATIONAL: ADR-0012 profit_take_1 (30%) - PROFIT_ARMED (T12_Progress 97.4%) + tick (b) conviction COLLAPSE across the four snapshots (HOLD69/HOLD59/NOTRADE0/AVOID0), the deterioration G1 was waiting for; tick (c) borderline (Est_4W already negative). G1 n/a (AVOID cv0, not a fresh breakout >=80); tick (b) fires regardless of G1 per ADR-0012. US-19: this is the SAME profit-take first fired 07-16, unexecuted through four EODs, now RE-VERIFIED on a genuine conviction collapse and repriced +2.3% higher to 212.06 - size NOT escalated (still 30%). Valuation MoS -2.34 > -3, no amplify (G2 suppresses anyway). Keep 70, trail-raise 200..00 (EMA100 200.88 cluster; scan chandelier looser). Proceeds Cross-book: execute ONCE here (L7); NVDA shared with ussemicon. · news |
| GOOGL | Alphabet Inc. Class A | 342.09 | HOLD | 342.09 | 345.00⚠ | 347.02 (+1.4%) | 355.24 (+3.8%) | 375.97 (+9.9%) | Alphabet's Q2 print landed after the 07-22 close: a clean beat - EPS, revenue vs expected, Google Cloud +82% - but capex guidance came in heavy and the shares were FLAT after hours, so the report neither rescued the stock nor broke it. A strong quarter is not a sell thesis, and the twelve-week forward is alive at +9.9%, so we hold. OPERATIONAL: the regular session closed 342.09, a MARGINAL -0.84% breach of the 345 hard line, but that is the LAST PRE-DIGESTION close - the report dropped 07-22 AMC. Per the prior card, 345 is the hard invalidation THROUGH the print and the decision point is the POST-EARNINGS SETTLED CLOSE (07-23): a confirmed 07-23 settle below 345 converts this to a full exit at the next EOD; a reclaim of 345 holds. Do NOT dump into the 07-23 open on a flat-reaction beat (US-12 / catalyst-hold discipline - the KLAC marginal-breach that recovered). Armed (T12 90.99) + tick (d) 4x NO TRADE fires mechanically, but tick (c) does NOT (forward +9.9% alive) and US-17 forbids a bare NO-TRADE dispose. Monitor leads on the breach; 345 stays the line. · news |
| KLAC | KLA Corporation | 214.69 | HOLD | 214.69 | 205.00 | 217.54 (+1.3%) | 217.46 (+1.3%) | 228.74 (+6.5%) | Book's largest position (, +22.2%) and its best-quality semicap name. Held through the -1.3% pullback to 214.69, still far above every structural line. OPERATIONAL: armed (T12 93.86, GainATR 2.76) + tick (d) 4x NO TRADE fires mechanically, BUT tick (c) does not (Est_12W 228.74 = +6.5% alive), US-17 forbids a bare NO-TRADE dispose, and Q4 earnings land 07-23 (next session, +/-8%) - squarely inside the <=5-session catalyst-hold window, which mandates hold/trail and NO pre-trim absent a confirmed lower-high or decisive stop break. Armed-but-not-fired -> mandatory trail-raise. Keep the 205.00 line (above EMA100 197.67, below the swing low). Post-print, a decisive 07-23 close below 205 or a confirmed lower high converts this to a trim at the next EOD. |
| MU | Micron Technology, Inc. | 959.48 | HOLD | 959.48 | 880.00 | 963.59 (+0.4%) | 1000.76 (+4.3%) | 1023.19 (+6.6%) | Held at 959.48 (+11.6% on the blended 859.49 cost, now risk-free above cost); the 30-share 07-21 discretionary add is +10.5%. OPERATIONAL: the AVOID cv49 with Stop_Price 1113.28 sitting ABOVE the close is the short-side structural artifact (systemic #3), NOT a sell - Portion 0, no Sell_Rank, and long-only means AVOID != short. Armed via T12 (93.77) but tick (c) does not fire (Est_12W 1023.19 = +6.6% alive, Est_4W 1000.76 = +4.3%) and there is no second warning code -> no profit-take. Keep the trail at 880.00 (do NOT lower it - 1.07 ATR below the prior 970.82 close would be ~877, lower than the standing line; a trail never ratchets down). HBM-sold-out overlay unbroken; SK Hynix read-through 07-29. |
| NBIS | Nebius Group N.V. | 218.16 | HOLD | 218.16 | 190.00 | 218.79 (+0.3%) | 240.46 (+10.2%) | 319.77 (+46.6%) | Held at 218.16 (+3.1% on the 211.60 cost) with the strongest forward in the book by far - Est_4W 240.46 (+10.2%), Est_12W 319.77 (+46.6%). OPERATIONAL: NOT armed (no Exit_Warning, T12 only 68.22) so the profit-take path is not even open; the AVOID cv64 with Stop_Price == Close is the same degenerate short-side artifact (systemic #3), Portion 0. Keep the 190.00 trail (above EMA100 186.88) - do not choke a +46% forward - ahead of Q2 earnings 07-29 (+/-15%, the widest band in the book); revisit the trail as the date approaches. Keep-core overlay live (Meta-deal invalidation NOT triggered). |
| LLY | Eli Lilly and Company | 1163.01 | HOLD | 1163.01 | 1120.00 | 1169.95 (+0.6%) | 1186.01 (+2.0%) | 1196.27 (+2.9%) | Held at 1163.01 (-1.1% on the day) with a drifting HOLD cv51 (50/44/48/51 - a -5 wobble, nowhere near the -20 tick-(b) bar). OPERATIONAL: armed (T12 97.22) but tick (c) does not fire (Est_12W 1196.27 = +2.9% alive, barely) and the label is HOLD not NO TRADE -> armed-but-not-fired -> hold/trail. Keep the 1120.00 line (scan chandelier 1092.06 is looser; keep the higher line). Far above EMA100 1070 / EMA200 1007. Pharma-onshoring tariff step 07-31 (+/-3%). |
| META | Meta Platforms, Inc. | 627.17 | HOLD | 627.17 | 620.00 | 627.62 (+0.1%) | 598.36 (-4.6%) | 616.04 (-1.8%) | Held at 627.17, now -1.2% UNDERWATER on the 635.00 cost with GainATR -0.32 (a LOSS). OPERATIONAL: the PROFIT_ARMED flag is a pure artifact for the third straight EOD (T12_Progress 101.8% only because Target_12Week 616.04 sits BELOW the close) - a four-day-old losing position is not a profit to take; explicitly DECLINED (systemic #2). NO TRADE cv0 x4 (the familiar intraday-HOLD-to-close-fade, L4/US-7). EMA100 621.28 / EMA200 639.41 straddle the 620 line; keep stop 620.00. Q2 earnings 07-29 AMC (+/-8%) is a direct book event 4 sessions out - the 4wk Est 598.36 (-4.6%) reflects that event risk. |
| OKTA | Okta, Inc. | 136.69 | HOLD | 136.69 | 124.00 | 138.76 (+1.5%) | 138.44 (+1.3%) | 141.62 (+3.6%) | NEW position - the book BOUGHT 200 @ 139.80 on 07-22 as a discretionary/unledgered add (OKTA was the 07-22 top near-miss at adj 64, one point under the floor and the only quality-passing buy in a month; no buy card proposed it, so this is drift, noted not criticised). Now HOLD cv59 at 136.69, -2.2% underwater. OPERATIONAL: the PROFIT_ARMED flag is an artifact (position is a LOSS, GainATR -0.36; T12 96.5% only because Target_12Week 141.62 hugs the close) - decline it. Modest positive forward (Est_12W 141.62, +3.6%). Set a protective stop at 124.00 ( the scan chandelier 123.84) so the fresh add is risk-defined. Quality gate PASSES (F=7) - this is a keepable name, just bought a touch early. |
| SPCX | Space Exploration Technologies (muted) | — | HOLD | — | 135.00 | n/a | n/a | n/a | Muted (private, no public quote, absent from the scan) - held on the manual 135 stop, never synthesized, but news-assessed per the edge-case rule. News read: CONCERN, and sharpening. Secondary prints are -135 - AT or BELOW the 135 stop - and the first ~20% insider lock-up slice frees after Q2 results in late July with ~7% tranches following Aug/Sep/Oct, so a large supply overhang is imminent. Hold on the 135 stop; the moment SPCX appears in the scan with a non-null Close below 135 it auto-unmutes and becomes a full-exit trigger. Lock-up window 07--03 live. · news |
Outcome & track record
Accuracy at the time of this record.
89 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 →
-0.132 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.
23 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.