US — End-of-Day Verdict
NO ACQUIRE (buy pool all chase/extended GROWTH_PRICED_IN; MS adj75 quality-killed). ANTICIPATE: AAPL QUEUED-ANTICIPATE buy-stop @329.58 0.25x (3/3 prints cv73, relative strength, expires 07-22). DISPOSE: NBIS 150/300 @~171.77 (decisive 185 break, halve per keep-core+G2, stop 152); GLW 150/150 FULL EXIT @~158.39 (2nd decisive 165 break + sustained bearish + downgrade, -20% loser); SNDK 8/15 @~1411 (profit_take_2 armed 112%+trail-break+dead-fwd; keep 7 trail 1300); NVDA 30/100 @~207.40 (carried re-affirm profit-take, US-19 30%, keep 70 trail 197.06). AMD 07-16 buy WITHDRAWN (WATCH cv46, -7.1%). Holds: GOOGL stop 345 catalyst-hold thru 07-22; KLAC trail 210.15; LLY 1106; MU 855 (#1 watch marginal breach); SPCX muted 135. 2nd-day AI-hardware washout -> cut the loser fully, halve the decisively-broken NBIS, bank two rolling-over winners, plant only a tiny strength-gated anticipate. Net + cash raised.
Recommendations
1 to acquire · 4 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 |
|---|---|---|---|---|---|---|---|---|---|
| AAPL | Apple | 333.26 | BUY-STOP — QUEUED @329.58 | 329.58 | 303.99 | 336.16 (+2.0%) | 335.69 (+1.9%) | 344.02 (+4.4%) | Standout relative-strength name -- AnticipationUp_VCP printed 3 of the last 3 snapshots at cv73 while AI-hardware craters (RSI 71.4 near 52W highs is itself the bull case). Self-limiting buy-stop into the washout; sized 0.25x (0.5x anticipate x 0.5 MoS<=-3) deliberately tiny. Entry sits just below close so likely fills near the open; expires +3 sessions. no_chase_queue counterfactual (+5.56 cost) argues for the strength-gated participation. |
| NBIS | Nebius Group | 171.77 | SELL 50% | 171.77 | 152.00 | 180.85 (+5.3%) | 192.55 (+12.1%) | 230.51 (+34.2%) | Decisive stop break (171.77 < 185, -7.15%) + first active RallySell_BearTrend + the prior explicit 'close <185' exit trigger fired on a -18.8% loser (below EMA50/100). Halve not full -- the overlay keep-core override stands and there is no confirmed Meta-cloud impairment (broad AI-cloud selloff, not a thesis break). Keep, reset stop 152 (just above EMA200); exit the rest on a close <152 or confirmed Meta impairment. Valuation amplify (MoS -6.18) G2-suppressed (DCF blank/hyper-growth). L2/US-17. |
| GLW | Corning | 158.39 | SELL ALL | 158.39 | — | 160.58 (+1.4%) | 157.62 (-0.5%) | 180.99 (+14.3%) | 2nd decisive stop break (158.39 < 165 reset, -4.01%) -- the 07-16 staged 'exit the rest on a 2nd decisive close <165' trigger fired -- plus sustained active RallySell_BearTrend (3 snapshots) and a still-live double-downgrade-to-sell on a -20.6% loser (below EMA50/100). Stable bearish-signal exit; the -9% follow-through matured the full exit. The lagging model +14.3% 12wk is exactly why this is a signal/stop exit, not a forward call. L2/US-17. |
| SNDK | Sandisk | 1411.08 | SELL 50% | 1411.08 | 1300.00 | 1467.71 (+4.0%) | 1370.65 (-2.9%) | 1259.87 (-10.7%) | ADR-0012 profit-take escalated to profit_take_2 (50%): PROFIT_ARMED (112% of target) + decisive break of my self-set 1520 trail (-7.17%) + dead forward (Est_12W -10.7%) + 3 consecutive NO TRADE = 2+ ticks. Honoring my own broken trail = a stop-driven reduction, not a gratuitous re-fire. Supercycle intact (above EMA100/200) -> keep, reset trail 1300. Valuation amplify (MoS -4.77) G2-suppressed (DCF << T12, hyper-growth). L3/US-13/US-19. |
| NVDA | NVIDIA | 207.40 | SELL 30% | 207.40 | 197.06 | 208.02 (+0.3%) | 207.76 (+0.2%) | 205.25 (-1.0%) | Re-affirm of the carried 07-16 pending profit-take, re-priced to 207.40 (4th-priority de-risk, honored not dropped). ADR-0012 profit-take: PROFIT_ARMED (101%, at target) + dead forward (Est_12W 205.25 < 1.02x) + 3 consecutive NO TRADE. G1 n/a (cv0). US-19 caps the re-fire at first-fire 30%. Keep 70 (above all EMAs, bull case intact), trail-raise 197.06. Valuation amplify n/a (MoS -2.33 > -3; G2). L3/US-19. |
| GOOGL | Alphabet A | 354.46 | HOLD | — | 345.00 | 357.48 | 367.14 | 375.46 | Catalyst-hold through 07-22 Q2 earnings (overlay hard line 345; stop relaxed from 350.21 to avoid a pre-earnings shakeout on a +/-7% expected move). Flipped to AVOID FailedBreakout_Down but no decisive break (>EMA100/200), PROFIT_ARMED with forward +5.9% alive; overlay says no pre-trim. Trim only on a confirmed lower-high or a decisive close <345. |
| KLAC | KLA Corporation | 219.37 | HOLD | — | 210.15 | 221.39 | 221.10 | 226.90 | Armed (96.7% of target, +24.8%) with 4 consecutive NO-TRADE cv0 -- mechanically tick (d) but US-17/systemic#2: the NO-TRADE-cv0 is an artifact and the forward is +3.4% alive (Est_12W 226.90). Hold, do NOT fire the trim. KLAC Q4 earnings 07-23 -> hold-through. A NO-TRADE with a flattening/negative forward would fire. |
| LLY | Eli Lilly | 1169.17 | HOLD | — | 1106.00 | 1174.91 | 1205.03 | 1231.20 | cv51 FailedBreakdown_Up, armed (95.0% of target), forward +5.3% alive (Est_12W 1231.20). Chandelier 1092.63 < 1106 -> keep the higher protective line. Overlay defensive-anchor thesis unchanged; hard invalidation 975. |
| MU | Micron | 853.20 | HOLD | — | 855.00⚠ | 852.44 | 900.40 | 898.48 | MARGINAL stop breach only (853.20 < 855, -0.21%) -- US-12 vindicated holding marginal breaches (MU already recovered +4.9% off one). At breakeven (cost 855.84), AVOID RallySell_BearTrend but forward still positive (Est_4W +5.5%, Est_12W +5.3%) and still >> EMA100/200 (long-term uptrend intact); overlay HBM-sold-out thesis unbroken. Scan stop 1008.97 degenerate (systemic #1). Decisive-exit trigger: close < ~845 or an HBM crack. |
| SPCX | Space Exploration Tech Corp | — | HOLD | — | 135.00 | n/a | n/a | n/a | Private, no public quote -> absent from scan, muted on the verdict, news-assessed. Concern unchanged: insider lock-up overhang (first ~20% frees after Q2 results late July, ~7% tranches Aug-Oct). Hold on the manual 135 stop; auto-unmute when it appears in the scan with a non-null Close. |
Outcome & track record
Accuracy at the time of this record.
76 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 →
-0.071 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.