US — End-of-Day Verdict
NO ACQUIRE (8th consecutive) | DISPOSE 3: META exit 60, GOOGL exit 100, NVDA -30 | KLAC trail raised 210
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, Inc. | 606.10 | SELL ALL | 606.10 | 620.00⚠ | 604.87 (-0.2%) | 583.78 (-3.7%) | 604.04 (-0.3%) | Exit the full 60-share Meta stake: it closed 606.10, a decisive break of the 620 stop, is ~4.6% underwater on the 635 cost, and the model projects flat-to-lower across every horizon (1wk -0.2%, 4wk -3.7%, 12wk -0.3%) into a +/-8% Q2 print on 07-29 (3 trading days). After Alphabet's capex-driven -7% selloff, Meta already sold off in sympathy and faces the identical capex-guidance test in 3 days -- we do not hold a broken loser into that binary. Basis: L2 stop-break (620) + negative 12wk (Est_12W 604.04 < close 606.10) on an underwater position -- a signal-based exit (CLAUDE.md S9), not a bare NO-TRADE dispose (US-17). PROFIT_ARMED is the known artifact (T12 100.3% because target < close, GainATR -1.13, a LOSS) -- ignored. Executes at the 07-24 open, pending (L8); reprice if the open gaps >~1.5%. Proceeds. · news |
| GOOGL | Alphabet, Inc.- Class A | 317.69 | SELL ALL | 317.69 | 345.00⚠ | 327.85 (+3.2%) | 333.90 (+5.1%) | 367.19 (+15.6%) | Exit the full 100-share Alphabet stake: the post-earnings SETTLED close is 317.69, a decisive -7.9% break of the 345 hard line the last two cards pre-committed to exit on. Q2 beat (EPS 9.11, rev 119.8B, cloud +82%) but 2026 capex was hiked to -205B, FCF swung to -, the buyback was suspended and multiple PT cuts followed -- a genuine name-specific fundamental repricing, not a technical head-fake. This is the confirmed <345 settle the 07-22/07-23 cards defined as a full-exit trigger; the reaction was a -7% gap-down, not the benign flat print the hold-through-earnings thesis was conditioned on. Name-specific breakdown -> full exit (US-12 carve-out; the semis actually rose today, so this is idiosyncratic, not a sector rout). The model still shows a positive forward (1wk +3.2%, 4wk +5.1%, 12wk +15.6%) and RSI 31 is oversold -- we honor the hard pre-committed stop over the model's mean-reversion hope (loss-minimization is the primary objective). Executes at the 07-24 open, pending (L8); reprice if the open gaps >~1.5%. Proceeds. · news |
| NVDA | NVIDIA Corporation | 208.76 | SELL 30% | 208.76 | 201.00 | 209.27 (+0.2%) | 208.25 (-0.2%) | 212.35 (+1.7%) | Trim NVDA (bank a third): ADR-0012 profit_take_1 -- armed (PROFIT_ARMED, T12_Progress 98.3%) + tick (c) dead forward (Est_12W 212.35 < 1.02x close 212.94) + tick (d) repeated NO TRADE. Forward is dead-flat (1wk +0.2%, 4wk -0.2%, 12wk +1.7%) at 98.3% of the 12wk target = spent risk/reward on the marginal third. US-19: this is the SAME fire first carded 07-16/07-23 that the book never executed while it round-tripped 212..76 -- re-affirmed and repriced, NOT escalated, still 30%. Keep the 70-share core (above EMA100/200). Trail the remainder at 201.00. Executes 07-24 open, pending (L8); reprice if it gaps >~1.5%. Proceeds Shared with ussemicon -> executes ONCE (L7). |
| KLAC | KLA Corporation | 218.73 | HOLD | 218.73 | 210.00 | 220.86 (+1.0%) | 221.23 (+1.1%) | 232.43 (+6.3%) | Hold the 1000-share KLA position (largest in the book, +24.5% on the 175.75 cost) and RAISE the trail. Armed (T12 94.1%, GainATR 3.43) + tick (d) chronic NO TRADE would mechanically fire a profit-take, but the Q4 07-23 catalyst resolved BULLISH -- the stock made a HIGHER close (214..73, +1.9%), not the <205 settle or confirmed lower-high the prior card set as the trim trigger. Forward alive (+6.3% 12wk). Ride the winner (US-20 / NBIS post-mortem); the NO-TRADE tick is the known short-side artifact US-17 forbids acting on bare. Trail 210 is above EMA100. Post-print lower-high or <210 settle -> trim next EOD. |
| MU | Micron Technology, Inc. | 990.21 | HOLD | 990.21 | 880.00 | 993.45 (+0.3%) | 1042.06 (+5.2%) | 1066.33 (+7.7%) | Hold 100 Micron, keep the trail at 880 (do not lower; +15.2% and risk-free above the 859.49 cost). Armed via T12 (92.9%) but tick (c) is alive (Est_12W 1066.33 = +7.7%, Est_4W +5.2%), there is no 2nd Exit_Warning code and the label is HOLD (not NO TRADE) -> armed-but-not-fired -> trail, don't trim. SK Hynix read-through 07-29. Closed +3.2% to 990.21. |
| NBIS | Nebius Group, N.V. | 220.97 | HOLD | 220.97 | 190.00 | 219.52 (-0.7%) | 242.46 (+9.7%) | 331.45 (+50.0%) | Hold 300 Nebius, keep the trail at 190 -- do not choke the strongest forward in the book (Est_4W 242.46 = +9.7%, Est_12W 331.45 = +50%). NOT armed (T12 66.7%) so the profit-take path is closed. Keep-core overlay live ahead of Q2 07-29 (+/-15%, widest band). Closed +1.3% to 220.97. |
| LLY | Eli Lilly & Co | 1185.87 | HOLD | 1185.87 | 1120.00 | 1196.06 (+0.9%) | 1212.80 (+2.3%) | 1231.69 (+3.9%) | Hold 70 Eli Lilly, keep the trail 1120. HOLD cv57 (rose, no -20 tick). Armed (T12 96.3%) but tick (c) alive (Est_12W 1231.69 = +3.9%) and label HOLD -> hold/trail. Pharma-onshoring tariff decision 07-31 (+/-3%). Closed +2.0% to 1185.87. |
| OKTA | Okta, Inc. | 136.10 | HOLD | 136.10 | 124.00 | 137.81 (+1.3%) | 136.00 (-0.1%) | 141.24 (+3.8%) | Hold 200 Okta on the 124 stop. The discretionary add (200 @139.80 on 07-22) is -2.6% underwater; PROFIT_ARMED is an artifact (a LOSS, GainATR -0.46) -- declined. Quality gate PASSES (F=7); a keepable name bought a touch early. Modest positive forward (Est_12W +3.8%). Closed -0.4% to 136.10. |
| SPCX | Space Exploration Technologies (muted) | — | HOLD | — | 135.00 | n/a | n/a | n/a | Hold 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 imminent. Auto-unmute + full-exit test the moment a scan Close < 135 prints. |
Outcome & track record
Accuracy at the time of this record.
90 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.