US — End-of-Day Verdict
NO ACQUIRE (JPM adj69 top near-miss, clean non-extended PullbackBuy Rank1 but quality-gate-killed F=2; OKTA/MS sub-floor -- US-20 5th straight session). NO ANTICIPATE (AAPL buy-stop withdrawn, never triggered). DISPOSE: GLW 150/150 FULL EXIT @~153.10 (stable bearish x4 + decisive break + fell on an up day = idiosyncratic crack, -23% loser); SNDK 8/15 @~1390.95 (profit_take_2 armed 115.9% + dead 12wk + 4x NO TRADE; keep 7 trail 1300); NVDA 30/100 @~203.28 (profit_take_1 armed 99% + dead forward; keep 70 trail 197). Holds: KLAC marginal breach -> hold through 07-23 earnings, decisive line reset 200.51; GOOGL 345 catalyst-hold 07-22 (intraday sell faded again); META stop SET 620 (armed flag is an artifact on a +1.7% 2-day-old position); MU breach resolved 855; NBIS 152 fwd +26.1%; LLY 1106; SPCX muted 135. A pure de-risking session on a relief bounce: cut the one idiosyncratic loser, bank partials on two armed winners at target, hold everything else through the 07-22/23 catalysts, and carry of into the event-dense 07--31 window. Net +raised.
Recommendations
0 to acquire · 3 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 |
|---|---|---|---|---|---|---|---|---|---|
| GLW | Corning Incorporated | 153.10 | SELL ALL | 153.10 | — | 157.02 (+2.6%) | 156.23 (+2.0%) | 161.19 (+5.3%) | Corning has broken down decisively and is now the only holding still falling while the rest of the book bounces. The stock has printed a stable bearish signal for four straight snapshots, sits 7% below its stop and 10% below its 100-day trend line, and the earlier double-downgrade-to-sell plus a deeply stretched valuation (fair-value margin -11.3) all point the same way. This is a -23% loser whose thesis has cracked on its own merits rather than with the sector, so we cut the whole position rather than trimming. Operational: exit basis is stable AVOID x4 + decisive break of the 165 reset (close 153.10) + relative weakness on an up day (US-22 idiosyncratic-crack branch). L2/L3 apply; the lagging Est_12W of +5.3% is explicitly overridden per US-23 (forward lags a confirmed breakdown) and must not veto a signal/stop exit. Trim-discipline G1-G3 do not apply (they protect uptrending winners). 07-28 Q2 earnings is 6 sessions out, outside the <=5-session catalyst-hold window. Proceeds realized ~-Sell-cell FailedBreakout_Down_20D|sell has decayed to +0 (n=8) so the basis is stability + the stop break, not the cell. |
| SNDK | Sandisk Corporation | 1390.95 | SELL 50% | 1390.95 | 1300.00 | 1428.44 (+2.7%) | 1385.08 (-0.4%) | 1200.54 (-13.7%) | Sandisk has run 16% past its twelve-week target and the model's forward view has now gone negative (-13.7%), while the signal engine has fallen silent for four straight snapshots. That combination is the textbook case for banking half a winner rather than waiting for the reversal to announce itself. The NAND/HBM supercycle looks intact - the stock still sits above its 100- and 200-day trend lines and next week brings SK Hynix, Samsung and Lam Research read-throughs - so we keep the other half running with a raised trail. Operational: ADR-0012 profit_take_2, armed at T12_Progress 115.9% with ticks (c) dead 12wk forward [1200.54 < 1.02x1390.95 = 1418.77] and (d) 4x consecutive NO TRADE. Self-set 1300 trail is INTACT - pure armed + soft-2-tick fire, not a trail break. US-19: same 50% first-fire repriced +2.7% higher from 07-18, re-verified at the settled close, NOT an escalation. Valuation amplify (MoS -4.77 <= -3 would bump is G2-SUPPRESSED (DCF 1005.14 << Target_12Week, Rev_Growth 0.98 hyper-growth). Keep, trail 1300. Est_12W exceeds the DCF anchor 1005.14. Proceeds. |
| NVDA | NVIDIA Corporation | 203.28 | SELL 30% | 203.28 | 197.00 | 203.49 (+0.1%) | 202.54 (-0.4%) | 205.37 (+1.0%) | Nvidia has reached its twelve-week target and the model now projects essentially no further upside over that horizon - a flat +1.0%. Taking 30% off at target while the signal is still healthy is the disciplined way to bank a completed move without abandoning the position. We keep running into the late-July cloud-capex cluster (Microsoft Azure on 07-29, AWS on 07-30), which is where the next leg would have to come from, protected by a raised trailing stop. Operational: ADR-0012 profit_take_1, armed at T12_Progress 99.0% with a single tick (c) dead forward [Est_12W 205.37 < 1.02x203.28 = 207.35]. Ticks (b) and (d) do NOT fire - conviction flat at 61 (dipped to 54 intraday, recovered by the close) and the label is HOLD, not NO TRADE. G1 does not apply (cv61 < 80, not a fresh breakout). US-19: first-fire 30% held and repriced from 07-16/17/18, NOT an escalation. Trail-raise to 197 (scan chandelier 188.47 is looser; keep the higher manual line). Est_12W exceeds the DCF anchor 163.98. Proceeds. |
| JPM | JPMorgan Chase & Co. | 338.87 | NO ACTION | 336.86 | 326.85 | 340.94 (+1.2%) | 347.32 (+3.1%) | 358.48 (+6.4%) | JPMorgan is the best buy setup the book has seen in over a week - a clean pullback entry, top-ranked, not extended, and on the one signal family that has actually been paying - but it is blocked by the fundamental quality screen, which scores the bank poorly on balance-sheet strength and reads it as expensive against its book value. We are not overriding that screen to force a trade, so this is a deliberate pass rather than an opportunity missed by accident. Operational: adj 69 = cv66 PullbackBuy_VWAP (Buy_Rank 1) + val_adj -1 (MoS -0.29) + bias +4; clears the 65 floor and is NOT extended (eD -0.23, close 338.87 vs entry 336.86). Hard quality gate: Quality_Pass False, F-Score 2, OVERVALUED_VS_RI (residual-income model applied to a bank - see systemic finding #1). Ledgered direction:none/optional:true so the counterfactual grader prices what the veto costs (US-20 evidence, 5th consecutive session). Re-arm: only if Quality_Pass flips True on a fresh fairvalue run while the PullbackBuy print and the non-extended entry hold. |
| KLAC | KLA Corporation | 207.60 | HOLD | 207.60 | 200.51 | 209.38 (+0.9%) | 207.61 (+0.0%) | 217.03 (+4.5%) | KLA slipped 2.4% and closed just below its trailing stop, but the miss is small (1.2%) and fiscal Q4 results land in two sessions. Trimming the book's largest position into its own earnings print on a marginal breach is the wrong trade; we hold through the event on a lowered, clearly-defined line and let the results decide. The twelve-week view is still positive at +4.5%, and the position remains +18% above cost. Operational: marginal breach (207.60 vs 210.15 trail, -1.21%, inside the ~1.5% decisive bar) -> US-12 hold. Armed (T12_Progress 95.7%) with 4x NO TRADE cv0 = mechanical tick (d), but tick (c) does NOT fire (forward +4.5% alive) and US-17 (NoTrade|sell -4) bars a bare NO-TRADE dispose -> armed-but-not-fired = mandatory trail-raise, not a trim. Catalyst-aware hold through 07-23 Q4 (+/-8% band); no pre-trim (US-18). DECISIVE LINE RESET to a close below EMA100 200.51; the 210.15 trail becomes the post-earnings re-arm reference. Largest position at (~38% of equities) - book's #1 risk. A decisive break of 200.51 or a confirmed post-earnings lower-high converts this to a trim. |
| GOOGL | Alphabet Inc. Class A | 351.99 | HOLD | 351.99 | 345.00 | 354.14 (+0.6%) | 363.32 (+3.2%) | 380.36 (+8.1%) | Alphabet flashed a sell warning twice during Monday's session and then closed neutral - the fifth time this exact intraday head-fake has appeared in this book, and every prior instance faded. With Q2 results due after tomorrow's close and the twelve-week view still +8% higher, the right move is to hold through the print on a hard 345 line rather than sell into a signal that keeps evaporating. Operational: STRONG SELL - REDUCE cv71 printed at BOTH J20o30 and J20o60, FADED to NO TRADE cv0 at the settled close -> L4/US-7/US-11, never fire a dispose off an intraday print. Armed (T12_Progress 92.5%) but tick (c) does NOT fire (forward +8.1% alive, Est_12W 380.36); no stop break (351.99 > 345, > EMA100 347.53, >> EMA200 319.33). Catalyst-aware hold through 07-22 AMC earnings (+/-7% / +/-1.88 ATR); no pre-trim (US-18). Overlay hard invalidation 345 stands even through the print - close sits only 2.0% above it. |
| META | Meta Platforms | 645.85 | HOLD | 645.85 | 620.00 | 648.10 (+0.3%) | 623.95 (-3.4%) | 639.17 (-1.0%) | Meta is a new position, bought off-book two sessions ago and now up 1.7%, and it had no protective stop recorded - that is fixed here with a stop at 620, just under the 100-day trend support. The model's exit flag on this row is a false alarm and we are explicitly not acting on it. Q2 results on 07-29 are now a direct event for the book and carry a wide swing band, so we hold into them on the defined line. Operational: buy 60 @ 635.00 on 07-18, unledgered/human_cli; monitor untracked + no_stop warnings both closed by this card. NO TRADE cv0 x4. The PROFIT_ARMED flag is an ARTIFACT - Gain_ATR is 0.40 (vs the 3.0 arm) on a 2-session-old +1.7% position; it arms only via T12_Progress 101%, which reads 101% because Target_12Week 639.17 sits BELOW the 645.85 close. Firing a 50% profit-take here would be absurd -> declined (systemic finding #2: gate the T12_Progress arm path on Unreal_PnL_Pct > 0). Stop 620.00 = EMA100 620.73 support cluster (-4.0%); EMA200 639.90 sits at cost, too tight for ATR 27.26. 07-29 AMC earnings +/-8% / +/-1.74 ATR. |
| MU | Micron Technology, Inc. | 865.46 | HOLD | 865.46 | 855.00 | 870.76 (+0.6%) | 910.09 (+5.2%) | 906.38 (+4.7%) | Micron has recovered back above its stop after two shallow dips below it - the patient call was the right one, exactly as it was on 07-02. The memory thesis is intact, the stock sits far above its long-term trend lines, and the forward view is a healthy +4.7%. Hold, with SK Hynix's results on 07-29 as the next real test. Operational: BREACH RESOLVED - close 865.46 back above the 855 line (+1.2%) after two marginal sub-855 sessions (US-12 vindicated). Near-breakeven vs cost 855.84 (+1.12%). NO TRADE cv0 but forward positive (Est_4W 910.09 +5.2%, Est_12W 906.38 +4.7%); >> EMA100 750.44 / EMA200 567.59. Overlay HBM-sold-out thesis unbroken. Decisive-exit line unchanged: a close < ~845 OR an HBM pricing/demand crack. Scan Stop blank/degenerate (systemic #3) -> manual 855 stands. |
| NBIS | Nebius Group, N.V. | 182.62 | HOLD | 182.62 | 152.00 | 186.91 (+2.3%) | 196.79 (+7.8%) | 230.32 (+26.1%) | Nebius was the book's strongest performer on Monday, up 2.8%, and carries by far the best forward view of any holding at +26%. The Meta cloud relationship that underpins the thesis remains intact, so we keep the full position. Q2 results on 07-29 carry the widest swing band in the book, which is a reason to tighten the trail as the date approaches rather than to reduce now. Operational: NO TRADE x4, close 182.62 (+2.8%, best held name of the session). Not armed. Still below EMA100 185.64 but >> EMA200 150.67; -13.7% vs cost 211.60. Keep-core overlay override live (Meta-deal invalidation NOT triggered). Horizon flags Q2 earnings 07-29 at +/-15% / +/-1.14 ATR with a tighten-trail stance -> revisit the 152 line as 07-29 approaches. Exit the remainder on a close < 152 OR confirmed Meta-cloud impairment. |
| LLY | Eli Lilly & Co | 1146.90 | HOLD | 1146.90 | 1106.00 | 1147.78 (+0.1%) | 1179.70 (+2.9%) | 1194.18 (+4.1%) | Lilly wobbled during the session and recovered by the close, leaving the constructive setup intact and the twelve-week view still 4% higher. It sits comfortably above its long-term trend lines with no exit trigger, so we simply hold and keep the stop where it is. Operational: HOLD PullbackBuy_VWAP cv55 (dipped 48/44 intraday, recovered by the close - the same intraday-fade pattern as GOOGL/NVDA). Armed (T12_Progress 96.0%) but tick (c) does NOT fire (forward +4.1% alive, Est_12W 1194.18) -> armed-but-not-fired, hold. Stop 1106.00 retained (scan chandelier 1104.98 is lower; keep the higher line). Close 1146.90 >> EMA100 1066.34 / EMA200 1005.53. Overlay hard invalidation 975. Pharma onshoring tariff step 07-31 (+/-3%). |
| SPCX | Space Exploration Tech Corp | — | HOLD | — | 135.00 | n/a | n/a | n/a | SpaceX is a private holding with no public quote, so it carries no technical signal and is assessed on news alone. The picture is unchanged and cautious: insider lock-up shares begin freeing after Q2 results later this month and continue in monthly tranches through October, which is supply overhead rather than a thesis break. We hold on the manual stop. Operational: permanently ABSENT from the scan CSV (no_close) -> muted on the verdict, never synthesized; news-assessed per the eval-eod edge-case rule. Lock-up overhang: first ~20% frees after Q2 results late July, then ~7% tranches Aug-Oct. Horizon adds a bonus-tranche trigger observation window 07--03 (+/-6%, low confidence). Classify watch/concern. Manual stop 135. AUTO-UNMUTE and resume full signal+fusion treatment the moment it appears in the scan with a non-null Close. |
Outcome & track record
Accuracy at the time of this record.
84 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.