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 |
|---|---|---|---|---|---|---|---|---|---|
| SKHY | SK hynix Inc. | 170.50 | SELL 30% | 170.50 | 184.14⚠ | n/a | 172.32 (+1.1%) | 191.85 (+12.5%) | Cutting 30% of SK hynix: it now sits 7.4% below its 184.14 stop after memory stocks sold off despite Samsung's record quarter, but the 12-week view (+12.5%) and a fresh UNDERVALUED fair-value read keep this a risk-sizing cut, not an exit. Carried 10-07 fired trigger (unexecuted, UNRECONCILED); sector break -> trim + hold core (US-12/US-22); AVOID cv0 is a label crossing, no escalation (US-19/US-49); UNDERVALUED tier-down already at floor. Line held 184.14 (US-58). Escalation: SELL 70 more on a settled close <=169.04 on us_signals_20261010_06001x.csv..us_signals_20261014_06001x.csv. · news |
| KLAC | KLA Corporation | 196.72 | SELL 30% | 196.72 | 194.81 | n/a | 200.93 (+2.1%) | 194.12 (-1.3%) | Banking 30% of a +12% KLAC winner: the 12-week view (194.12) still sits below the close and the engine has been quiet for three sessions, so the forward case for full size is gone; the core rides the 194.81 trail into 10-28 earnings. Armed (Gain_ATR watermark 4.44, real cost; US-84) + tick c (dead 12wk -1.32%) + tick d (3rd NO TRADE, corroborated, US-71); soft ticks -> no escalation (US-19). 5th consecutive re-card (US-37 stalemate). Decisive break <=191.89; intraday low 191.09. |
| OKTA | Okta Inc. | 220.21 | SELL 30% | 220.21 | 203.45 | n/a | 231.46 (+5.1%) | 228.08 (+3.6%) | Banking 30% of a +57% OKTA winner after RSI divergence re-appeared at an RSI near 72 while conviction sits at a weak 49; the core stays on a raised 203.45 trail. Armed (Gain_ATR 9.60, real cost) + tick a RSI_DIV; carried 10-06 tick b basis unexecuted. RSI_DIV oscillated (10-06 on, 10-07 off, 10-08 on) -> held at the 30% floor, no escalation (US-19). MoS bump G2-suppressed (EPV 27.62 vs DCF 121.01). Trail 201.82 -> 203.45 (2.0 ATR, US-65). · news |
| NVDA | NVIDIA Corporation | 230.48 | NO ACTION | 230.48 | 228.72 | n/a | 238.59 (+3.5%) | 251.35 (+9.1%) | Nvidia went quiet for a second session as chip stocks sold off on AI-revenue worries; the 12-week view (+9.1%) is still alive, so this is a deferred 30% trim, not a live order. Tick d (2nd NO TRADE, corroborated by -2.94% close + RSI, US-71) on a T12-limb arm (91.7) blocked only by the blank Avg_Cost (US-55/US-66 deferred fire). Line 228.72; decisive <=225.29. · news |
| LLY | Eli Lilly & Co | 1169.60 | NO ACTION | 1169.60 | 1131.95 | n/a | 1208.96 (+3.4%) | 1249.57 (+6.8%) | Lilly's conviction fell from in one session; with a +6.8% 12-week view this is a deferred 30% trim, not a live order. Valid tick b from a bullish row (US-83); T12-limb arm (93.6) blocked by the blank Avg_Cost (US-55/US-33). Line 1131.95. |
| PLTR | Palantir Technologies Inc. | 198.78 | NO ACTION | 194.90 | 175.53 | n/a | 206.89 (+6.2%) | 203.35 (+4.3%) | Palantir prints a STRONG BUY (cv) but closed 0.62 ATR above its 194.90 entry and sits on the book's worst buy cell (BreakoutUp_20D, hit_4w 0/6) at a deeply growth-priced valuation; adjusted 70 clears the floor only narrowly. WATCH only: acquires vetoed while UNRECONCILED (US-56); no-chase -> re-arm at <=194.90 only while the next settled file still prints a buy trigger; size x0.5 (MoS <= -3). |
| NET | Cloudflare, Inc. | 341.89 | NO ACTION | 341.89 | 336.93 | n/a | 352.26 (+3.0%) | 384.24 (+12.4%) | HOLD cv64 -> cv59 at PullbackBuy entry, 12wk +12.4%. Written trigger SELL (30%) on a decisive settled close <=331.88 on us_signals_20261010_06001x.csv; lapses after that EOD. Line 336.93. |
| GOOGL | Alphabet, Inc.- Class A | 348.29 | HOLD | 348.29 | 342.20 | n/a | 360.32 (+3.5%) | 364.43 (+4.6%) | HOLD cv57 -> cv59, 12wk +4.6%, fresh FV UNDERVALUED; no tick. Blank Avg_Cost declines the T12 arm (US-55). Line 342.20. |
| MU | Micron Technology, Inc. | 1035.84 | HOLD | 1035.84 | 1022.05 | n/a | 1048.80 (+1.3%) | 1116.72 (+7.8%) | Armed (watermark 5.29) but no tick: cv76 -> 61 (-15, under the 20-pt tick), 12wk +7.8%, no warning; sector sell-the-news on Samsung's record prelim (US-30). Line 1022.05; decisive <=1006.72. · news |
| SPCX | Space Exploration Tech Corp | 160.57 | HOLD | 160.57 | 156.54 | n/a | 169.44 (+5.5%) | 184.56 (+14.9%) | BUY-ADD cv74 declined: entry 155.71 sits below the standing 156.54 line (incoherent add) and US-56 vetoes acquires. Hold through the 10-09 lock-up rung on 156.54. |
Outcome & track record
Accuracy at the time of this record.
282 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 →
-0.271 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.
91 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.