This website is for educational purposes only and does not constitute investment advice. Always do your own research and assess your own risk tolerance before making investment decisions.

US End-of-Day Verdict 24 Jul 2026, 16:00:00 GMT-4

US — End-of-Day Verdict

1 ACQUIRE (QUEUED AAPL @308.38, deep limit) | DISPOSE 3: GOOGL exit 100, META exit 60, NVDA -30 | HOLD NBIS through -15% crash (marginal break, +65.8% fwd), ride KLAC/MU pullbacks, LLY trail 1127

Recommendations

1 to acquire · 3 to dispose

TickerNameCloseActionAction 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
AAPLApple Inc.333.02BUY — QUEUED @308.38308.38298.50336.16 (+9.0%)338.69 (+9.8%)339.85 (+10.2%)Queue a starter Apple long on the pullback limit 308.38 - the first quality-passing (F=9) STRONG BUY on the reliable PullbackBuy_VWAP cell the book has thrown in a month, but the close (333) is 2.89 ATR past the model entry so we queue at the printed limit rather than chase. adj conviction 80 -10(val, GROWTH_PRICED_IN MoS -3.16) +3(scorecard) = 73, clears the 65 floor; size x0.5 (MoS <= -3) =>. expires 2026-07-29 (anchor +3 sessions). DEEP limit unlikely to fill - the model's own 1wk-low 316.83 sits above 308.38 (~7.4% retrace needed; no_chase_queue counterfactual +2.1% cost). Re-verify the PullbackBuy family + quality gate at any fill (US-8). 12wk 339.85 exceeds DCF 208.95.
GOOGLAlphabet, Inc.- Class A319.74SELL ALL319.74345.00327.27 (+2.4%)338.52 (+5.9%)374.51 (+17.1%)Exit the full 100 Alphabet - re-fire of the unfilled 07-24 exit. Decisive -7.3% break of the pre-committed 345 hard line (close 319.74) on a name-specific post-earnings capex breakdown (2026 capex -205B, FCF -, buyback suspended, PT cuts). The +0.6% dead-cat bounce and RSI 32 do not restore the thesis; the pre-committed stop governs (loss-min primary). Model forward is UPSIDE (12wk +17.1%) - this is a pure risk-discipline stop-break exit, not a forward call. GROWTH_PRICED_IN MoS -1.62, no valuation amplify. 12wk 374.51 exceeds DCF 154.23. Proceeds Executes Mon 07-27 open, pending.
METAMeta Platforms595.19SELL ALL595.19620.00593.17 (-0.3%)574.49 (-3.5%)592.94 (-0.4%)Exit the full 60 Meta - re-fire of the unfilled 07-24 exit. Decisive stop-break (620) on an underwater position (-6.27% on the 635 cost) with a flat-to-negative forward (L2: Est_12W 592.94 < close, Est_4W -3.5%); below the 620 stop and EMA100. Do not carry a broken loss into the Q2 print 07-29 (2 sessions out) amid the AI-capex punishment (capex-contagion after GOOGL). PROFIT_ARMED is a loss-artifact (GainATR -1.69) - ignored. FAIR_VALUE MoS -1.24, no amplify. Proceeds Executes Mon 07-27 open, pending.
NVDANVIDIA Corporation206.84SELL 30%206.84201.00207.18 (+0.2%)204.33 (-1.2%)208.91 (+1.0%)Bank NVIDIA (profit_take_1, ADR-0012) and keep the on a 201 trail. Armed (T12 99.0%) + tick (c) dead forward (Est_12W 208.91 < 1.02x close) + tick (d) 2 consecutive NO TRADE -> spent risk/reward at 99% of target. US-19: the SAME fire carded 07-16/07-23/07-24 that never executed, repriced 208..84, NOT escalated (still 30%). Shared with ussemicon -> execute ONCE (L7). GROWTH_PRICED_IN MoS -2.34, no amplify (> -3). 12wk exceeds DCF 163.98. Proceeds Executes Mon 07-27 open, pending.
NBISNebius Group, N.V.187.77HOLD187.77190.00193.01 (+2.8%)212.51 (+13.2%)311.36 (+65.8%)Hold 300 Nebius through a -15% crash; #1 watch, keep (do NOT widen) the 190 stop. The stop broke only -1.17% (marginal, not decisive) and the model forward is the book's strongest -- Est_4W +13.2%, Est_12W +65.8%; L2 needs stop-break AND neg-12wk and the 12wk is hugely positive, so L2 does not fire. Catalyst = Meta-cloud-competition fear + a debt raise, but the Meta deal is intact (Meta stays a customer) and multiple desks call the selloff oversold -- the overlay invalidation ('Meta deal materially at risk') is not cleanly triggered. News CONCERN but disputed. Do NOT pre-trim into Q2 07-29 (+/-15%, 2 sessions out; NBIS-miss discipline). A 2nd decisive settle below stop / confirmed Meta-deal breakdown -> full exit next EOD. · news
KLACKLA Corporation210.52HOLD210.52210.00212.65 (+1.0%)213.54 (+1.4%)223.49 (+6.2%)Hold the 1000-share KLA (largest position, +19.78% on the 175.75 cost), keep the 210 trail. Armed (T12 94.2%) + tick (d) 2x NO TRADE mechanically fires a profit-take, but G3 protects a winner: forward +6.2% alive (Est_12W 223.49), signal not bearish, and it held above the 210 trail (210.52 > 210). MoS -5.44 does not amplify -- G2 suppresses it (Target 223.49 >> DCF 93.26, unreliable on a hyper-grower). optional_trim counterfactual (-10.85% at 4wk) + US-20 say ride; first red day after the Q4 pop. Do not raise the trail into the pullback. A decisive <210 settle or confirmed lower-high -> trim 30% next EOD.
MUMicron Technology, Inc.920.95HOLD920.95880.00925.47 (+0.5%)973.42 (+5.7%)976.03 (+6.0%)Hold 100 Micron through a -7% pullback (still +7.15% on the 859.49 cost), keep the 880 trail. The flip HOLD cv53 -> NO TRADE cv0 mechanically fires tick (b) conviction-collapse, but the forward is alive +6.0% (Est_12W 976.03) and the news is overwhelmingly bullish (BofA PT UBS 2026 HBM sold out, record fiscal Q3, customers filled only 50-66% of demand) -- the down day reads as a pullback in a strong uptrend, not a break. Ride (optional_trim counterfactual + L1/US-20). Keep 880 (a trail never ratchets down). A decisive <880 settle or a 2nd NO TRADE with a rolling-over forward -> trim next EOD.
LLYEli Lilly & Co1196.03HOLD1196.031126.891208.17 (+1.0%)1223.80 (+2.3%)1242.84 (+3.9%)Hold 70 Eli Lilly and RAISE the trail.89 (the model stop). The lone strengthener this session -- conviction climbing -> on FailedBreakdown_Up_20D, closed +0.9% to 1196.03. Armed (T12 96.2%) but not fired (tick (c) alive: Est_12W +3.9%; label HOLD, no -20 tick) -> armed-but-not-fired = mandatory trail-raise. Pharma-onshoring tariff decision 07-31 (+/-3%).
OKTAOkta, Inc.138.50HOLD138.50124.00139.86 (+1.0%)137.23 (-0.9%)144.90 (+4.6%)Hold 200 Okta on the 124 stop. The 07-22 add (200 @139.80) is -0.93% underwater; closed +1.8% to 138.50. HOLD cv49 FailedBreakdown_Up_20D; PROFIT_ARMED is a loss-artifact (GainATR -0.18) - declined. Quality gate PASSES (F=7), keepable; modest forward (Est_12W 144.90, +4.6%). Keep 124.00.
SPCXSpace Exploration Technologies (muted)HOLD135.00n/an/an/aHold 160 SpaceX on the manual 135 stop; muted/private (no public quote, absent from the scan), news-assessed only. News read CONCERN, unchanged: secondary prints -135 sit at/below the stop and the first ~20% insider lock-up slice frees after Q2 (late July) with ~7% tranches Aug/Sep/Oct -- supply overhang. Auto-unmute + full-exit test the moment a scan Close < 135 prints.

Outcome & track record

Accuracy at the time of this record.

93 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.

This website is for educational purposes only and does not constitute investment advice. Always do your own research and assess your own risk tolerance before making investment decisions.