US — End-of-Day Verdict
ACQUIRE NO ACTION (0 of <=3) - 14th consecutive session with no admissible new BUY (US-20): AMZN adj 63 (quality-gate F=6 + extended -0.97 ATR, +5.1% past entry), SNOW adj 52 (cell -10, F=5), CRM adj 52 (F=7 but below EMA200), DDOG adj 51 (F=5), NET adj 51 (F=3, MoS -940). Zero PullbackBuy_VWAP candidates printed. ANTICIPATE 0 of <=1 - WDS (adj 74, F=4) and VIST (adj 78, UNDERVALUED, Quality_Pass True) both printed BUY - ANTICIPATE for the first time but each in only 1 of the last 3 snapshots (rule needs >=2). | DISPOSE 3 of <=3: META full exit 60 @ ~556.71 - L2 both legs, 9th session -10.21% below stop + dead 12wk, 2nd consecutive STRONG SELL - REDUCE, 8th re-fire; KLAC 50% trim @ ~182.82 - 2nd consecutive STRONG SELL - REDUCE cv76 Sell_Rank 1, adj 78 (highest in the book), US-18 satisfied, G2 suppresses the valuation amplify, keep-core 500; NVDA 30% trim @ ~200.75 - ADR-0012 armed (T12_Progress 100.61) + soft tick (c) dead forward, de-escalated from the pending 50%, execute ONCE vs ussemicon. | The session rotated out of the chip complex into the megacap laggard: GOOGL +6.73% to 356.13 (reclaimed all four EMAs, overlay healed), META +3.28%, NVDA +2.93%, against MU -5.90% giving back a third of the +18.4% bounce. | : buys sells free ->.
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 |
|---|---|---|---|---|---|---|---|---|---|
| META | Meta Platforms | 556.71 | SELL ALL | 556.71 | 620.00⚠ | 557.12 (+0.1%) | 549.03 (-1.4%) | 565.58 (+1.6%) | Exit the whole Meta position. Q2 revenue grew 28% to 8bn but earnings missed, free cash flow collapsed ~91% to and 2026 capex was guided up to ~$135bn - the market cut the stock 8% on the print and it has not recovered. The shares sit 10% below our stop for a ninth session, 12% under our cost, and below every moving average we track, while the model projects no recovery at any horizon out to 12 weeks. Valuation is only fair, so there is nothing cheap to wait for. | L2 fires both legs (decisive stop break -10.21% + dead 12wk: Est_12W 565.58 < 1.02x close 567.84). 2nd consecutive settled STRONG SELL - REDUCE (BreakdownDown_52W cv85 -> RallySell_BearTrend cv68, Sell_Rank 3). adj 63 sits below the 65 floor after the -5 RallySell_BearTrend|sell haircut, but L2 is an independent exit basis. MoS -0.92 > -3 so no valuation tier bump. 8th re-fire, repriced 539..71. Stop held at the broken 620.00 for monitor continuity until the exit fills. Analyst median PT noted and rejected - trade the signal. · news |
| KLAC | KLA Corporation | 182.82 | SELL 50% | 182.82 | 168.00 | 184.44 (+0.9%) | 187.56 (+2.6%) | 192.32 (+5.2%) | Halve our largest holding and keep the other half. KLA has now printed a top-ranked sell signal two sessions running, and the chart has broken down beneath its 20-, 50- and 100-day averages with only the 200-day still holding - the stock is 40% below its 52-week high. Set against that, the business itself is doing well: record fiscal Q4 revenue on AI-infrastructure and advanced-packaging demand, and Wall Street still rates it a Moderate Buy with an average target of (+23%). Intrinsic value says the opposite - the shares are richly priced. Selling half banks a solid gain while keeping a full stake in the recovery case. | 2 consecutive settled STRONG SELL - REDUCE cv76 Sell_Rank 1 = US-18 SATISFIED (J30C lone flip, J31C confirms); US-19 classes a stable SELL-REDUCE as a hard tick, immediately executable. adj 78 = highest in the book either side. G1 no protection (bearish signal, not a fresh breakout); G3 passes on its bearish-signal limb. G2 SUPPRESSES the valuation amplify - MoS -4.41 would bump but Est_12W 192.32 is 1.93x the 99.91 DCF anchor (unreliable), so no bump. Sized to the 50% tier not the engine's 88.52 per US-12/US-22 keep-core and all prior KLAC cards. ADR-0012 armed (T12_Progress 95.06, Gain_ATR 0.48, +4.02% over the 175.75 cost) but ZERO ticks - the profit-take contributes nothing; the trim rides on the stable REDUCE alone. Trail on the retained 500 stays 168.00, deliberately NOT raised to EMA200 171.19 - halving is already the de-risk, double-tightening into a 14.81 ATR invites a whipsaw. Re-arm on a 3rd bearish print or a close below 168.00. · news |
| NVDA | NVIDIA Corporation | 200.75 | SELL 30% | 200.75 | 188.00 | 200.21 (-0.3%) | 196.94 (-1.9%) | 199.54 (-0.6%) | Take 30% off Nvidia and keep 70. The position has reached its 12-week price objective, and the model now projects essentially nothing further in any direction - flat to slightly negative at one week, four weeks and twelve weeks alike. The stock rose 2.9% on the session as Amazon and Microsoft raised capital spending, and the order book is enormous (~$1tn of Blackwell and Vera Rubin commitments through 2027), but Nvidia is still 18% below its June high and has lagged every chip peer this year, with renewed questions about circular financing around the reported $250bn OpenAI backstop. Banking part of a fully-realised target while keeping the majority for the next product cycle. | ADR-0012 profit-take: ARMED on T12_Progress 100.61 (close-vs-target, needs no, so NOT the GOOGL loss-artifact) + soft tick (c) dead forward (Est_12W 199.54 < 1.02x close 204.77). One soft tick -> profit_take_1 30%, never more. DE-ESCALATED from the pending 07-31 50% card per US-19: the hard leg (3 consecutive STRONG SELL - REDUCE + broken stop) dissolved into NO TRADE cv0 with the close back above the 188 stop, so US-17 strips the signal-sell basis and only the profit-take survives. Tick (b) EXPLICITLY DECLINED - conviction is the sell case dissolving, not position deterioration. Tick (d) needs a 2nd consecutive NO TRADE; this is the first. MoS -2.07 > -3, no tier bump. Est_12W exceeds the 163.98 DCF anchor - annotated, not modified. SHARED WITH ussemicon - EXECUTE ONCE (L7). Retained 70 keep the 188.00 stop. · news |
| GOOGL | Alphabet, Inc.- Class A | 356.13 | HOLD | 356.13 | 329.00 | 357.98 (+0.5%) | 363.80 (+2.2%) | 385.49 (+8.2%) | Hold Alphabet and raise the stop to The stock jumped 6.7% - the biggest move in the book - as investors rotated out of the chip complex and back into a beaten-down megacap, reclaiming its 20-, 50-, 100- and 200-day averages in a single session. The model's sell flag appeared for the first time tonight, but a single flip on the day a stock breaks out in every direction is not a reason to sell; the 12-week view remains 8% higher. Cloud revenue grew 82% to 8bn with a $514bn backlog. | STRONG SELL - REDUCE cv73 Sell_Rank 2 NOT FIRED: a LONE flip out of 3 consecutive NO TRADE cv0, and US-18 requires a 2nd consecutive settled print or a close below invalidation - neither holds. Firing here would be the NBIS trim error in textbook form. Forward alive at every horizon (1wk +0.5%, 4wk +2.2%, 12wk +8.25%). ADR-0012 armed (T12_Progress 92.38) but zero ticks - tick (c) alive by a wide margin (385.49 vs the 363.25 threshold) - so trail-raise, not trim. Overlay '<345' override now HEALED, cleared by +3.2%. Stop 319..00 (model Stop_Price 329.02). RE-ARM on a settled close below 329.00 or a 2nd consecutive bearish print. · news |
| LLY | Eli Lilly & Co | 1148.84 | HOLD | 1148.84 | 1155.71⚠ | 1158.88 (+0.9%) | 1144.31 (-0.4%) | 1187.10 (+3.3%) | Hold Lilly into its Q2 report on 5 August. The shares slipped 0.5% and sit a fraction below our trailing stop - a marginal breach, not a decisive break - and the signal has been quietly weakening for four sessions. With earnings two trading days away and consensus looking for 30% revenue growth (Goldman keeps a Buy and a target), the disciplined move is to hold through the event rather than sell into it on a fractional stop touch. | Trail 1155.71 STANDS - a trail is never lowered, and the model Stop_Price 1076.75 prints below it; it will keep flagging on the monitor, correctly. Breach 0.59% = MARGINAL, 2nd consecutive session (same test that correctly held KLAC at -0.47% on 07-30). 7th consecutive FailedBreakdown_Up_20D but conviction DECAYING -> (-23 over 4 sessions; EOD-over-EOD -11, inside the -20 tick) - flagged as a deteriorating signal even without a label change. Armed (T12_Progress 96.78), tick (c) alive but THIN (1187.10 vs the 1171.82 threshold, +1.3% headroom). Catalyst-aware HOLD per the trim-discipline gates: Q2 08-05 BMO is inside 5 sessions, so trim only on a confirmed lower-high or a decisive break. Lost EMA20 1176.33; holds EMA50 1138.13 / EMA100 1085.51 / EMA200 1018.90. ACTION THRESHOLD: a DECISIVE close below 1120.00, or a post-earnings breakdown. · news |
| MU | Micron Technology, Inc. | 823.03 | HOLD | 823.03 | 770.00 | 823.22 (+0.0%) | 913.15 (+10.9%) | 1064.94 (+29.4%) | Hold Micron. The stock gave back 5.9%, roughly a third of Thursday's 18% surge, but it remains comfortably above our stop and above its 100-day average, and the 12-week view is still nearly 30% higher. The model has no active signal either way, which on its own is never a reason to sell. | -5.90% to 823.03, back to -4.24% under the 859.49 cost, but +6.9% above the raised 770.00 stop and above EMA100 772.72; below EMA20 907.41 / EMA50 892.61. NO TRADE cv0 is never a dispose basis (US-17). NOT armed (T12_Progress 77.28, no PROFIT_ARMED flag). The 07-30 trim stays WITHDRAWN and survives its first real test - nothing re-arms. 12wk band [459.70-1795.81] = 3.9x wide, near-uninformative (systemic 4). AMD Q2 on 08-04 carries an HBM read-through. Overlay invalidation (HBM pricing cracks / decisive stop break) UNTRIGGERED. Stop 770.00 stands. |
| NBIS | Nebius Group, N.V. | 190.41 | HOLD | 190.41 | 153.00 | 198.91 (+4.5%) | 215.11 (+13.0%) | 300.44 (+57.8%) | Hold Nebius. Up another 1.1%, extending the recovery from last week's washout, and now back above both its 100- and 200-day averages. Still 10% under our cost, but the 12-week view is materially higher and there is no active sell signal. | +1.05% to 190.41, -10.01% under the 211.60 cost. NO TRADE cv0 (US-17). Holds EMA100 186.57 and EMA200 154.29; below EMA20 198.16 / EMA50 204.78. NOT armed (T12_Progress 63.38). 12wk 300.44 = +57.8% but the band [112.69-584.41] is 5.2x wide - near-uninformative (systemic 4); do not size off it. No confirmed Meta contract impairment -> the overlay override remains UNTRIGGERED. Q2 ~08-12. Stop 153.00 stands. |
| OKTA | Okta Inc. | 141.93 | HOLD | 141.93 | 132.00 | 143.04 (+0.8%) | 146.88 (+3.5%) | 160.14 (+12.8%) | Hold Okta and raise the stop to This is the one holding whose signal is actually strengthening - conviction improved for a third straight session and the position is now back above our cost, with the model pointing roughly 13% higher over twelve weeks. Raising the stop locks in the recovery without crowding the trade. | +1.08% to 141.93, +1.52% over the 139.80 cost. 3rd consecutive FailedBreakdown_Up_20D with conviction improving -> 64 - the only strengthening held name in the book. Forward +0.8% / +3.5% / +12.8%. NOT armed (T12_Progress 88.63 < 90, Gain_ATR 0.33 << 3.0). Model Stop_Price 137.76 is only 0.64 ATR below the close - too tight to adopt; 132.00 sits ~1.5 ATR below and under EMA20 138.88. Well clear of EMA50 126.93. Stop 130..00. |
| SPCX | Space Exploration Tech Corp | — | HOLD | — | 135.00 | n/a | n/a | n/a | Hold SpaceX on the manual stop, but be aware this is the most event-loaded name in the book and both catalysts land within days. The company reports its first-ever quarterly results as a public company on 4 August, with no reporting history and no established guidance to anchor expectations. Two trading days later, on 6 August, roughly 911.5m shares - about $116bn worth - become eligible to trade in one of the largest lock-up expirations in recent market history. Morgan Stanley argues the fundamentals are largely unchanged and the pressure creates an entry point; we are not adding into it. | Private/unquoted, permanently absent from the scan - muted on signals (no action, conviction, entry or targets synthesised), news-assessed every run per the edge-case rule. Maiden Q2 08-04 AMC (8bn revenue, ~-EPS expected); stock ~47% off its post-IPO high and below the Jun-12 offer price. Lock-up 08-06 staggered: ~20% post-earnings, then ~7% tranches ~08-21 and ~09-10 - insiders could sell up to ~44% by early September. Musk + core insiders locked to mid-2027. Float expansion opens Nasdaq-100 / Russell index-eligibility mechanics from 08-07, no confirmed effective date. Horizon bands: earnings +/-18%, lock-up -25%/+10%. A scan Close < 135.00 AUTO-UNMUTES and becomes a full-exit trigger. · news |
| AMZN | Amazon.com Inc | 271.58 | NO ACTION | 258.34 | 215.89 | 273.32 (+5.8%) | 278.00 (+7.6%) | 285.17 (+10.4%) | Not buying Amazon despite the strongest buy signal in the book. Ledgered so the counterfactual grader prices what declining it cost or saved. | Top-ranked STRONG BUY cv80 Buy_Rank 1 on BreakoutUp_20D, TRIPLE-BLOCKED: (1) cell bias -7 plus val_adj -10 (MoS -1.93) -> adj 63, below the 65 floor; (2) Quality_Pass FALSE (F=6) blocks new entries outright; (3) EXTENDED - Entry_Distance_ATR -0.97 with the close 271.58 sitting +5.1% past the 258.34 model entry after a one-session jump from 235.50 (AVOID cv78 the night before). Chasing this is the exact L6/US-9 failure mode. Not queued: the entry is 5% below the market and the quality gate would still block a fill. |
| VIST | Vista Energy, S.A.B. de | 70.45 | BUY-STOP | 71.23 | 61.99 | 70.72 (-0.7%) | 71.44 (+0.3%) | 74.86 (+5.1%) | Not queuing Vista Energy tonight, but flagging it as the best new-entry prospect this book has produced in weeks. It is the first candidate in a long stretch that is both attractively valued on intrinsic worth and passes our quality screen, and it trades above every moving average we track. The anticipation signal appeared only tonight, and our rule requires it to persist before we commit capital. | BUY - ANTICIPATE cv76, val_adj +2 (UNDERVALUED, MoS +0.08, Quality_Pass True, F=7, DCF 86.44 vs close 70.45) -> adj 78, comfortably over the 55 anticipate floor. INELIGIBLE on ADR-0012's >=2-of-3 snapshot test: printed BUY - ANTICIPATE in exactly (J29C/J30C were WATCH cv56 / cv50 on FailedBreakdown_Up_20D). Above EMA20 66.58 / EMA50 67.23 / EMA100 66.01 / EMA200 61.39; RSI 59.4, not extended. Directly relevant to the US-20 systemic finding - the first Quality_Pass-True buy source in weeks. RE-ARM: if it prints BUY - ANTICIPATE again on 08-03 it becomes slot-eligible and should be queued as a GTC buy-stop at the then-current Entry_Price, 0.5x normal new-BUY. |
Outcome & track record
Accuracy at the time of this record.
109 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.