Recommendations
0 to acquire · 0 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 |
|---|---|---|---|---|---|---|---|---|---|
| NVDA | NVIDIA Corporation | 238.90 | HOLD | 238.90 | 224.76 | 251.77 (+5.4%) | 281.80 (+18.0%) | 269.22 (+12.7%) | NVIDIA closed at a second straight record (238.90, +2.12%) on Foxconn's +47% Q revenue, but the model cooled to HOLD 63, so the core is held and not added to. Not armed (T12 88.74, Gain_ATR 2.13), so the stop stays 224.76 (2.48 ATR; the engine's 217.68 is lower and a stop is never lowered). W1: settled close < 224.76 -> sell 30%; < EMA200 204.41 -> full exit. f=0.30 estimates; the 12wk exceeds the DCF anchor 175.43. · news |
| TSM | Taiwan Semiconductor Manufacturing C | 485.80 | NO ACTION | 485.80 | 464.78 | 474.52 (-2.3%) | 448.21 (-7.7%) | 557.24 (+14.7%) | TSMC hit an all-time high (485.80, +2.75%) on Elon Musk confirming early Terafab talks, but the model flipped to AVOID 59 (ReversalDown_Overbought, RSI 75.6). That is an overbought warning, not a reduce instruction, so the-share stub is held with a raised stop. Genuinely PROFIT_ARMED (Gain_ATR 4.21, +10.91%) but not fired: (a) no other code; (b) is a cross-family rise (U5-style, assumption); (c) 12wk 557.24 > 495.52; (d) no NO TRADE. Mandatory trail-raise 457.98 -> 464.78 (chandelier 487.46 - 2 x 11.34; 1.85 ATR, U2 ok). W1 trigger (fresh basis, first instance arms): a 2nd consecutive sell-family print, a settled close < 464.78, or any fire tick -> full exit of at the next open (T5 stub). 1wk/4wk come from the bearish row's own target; the 12wk is the engine's (contradictory). Ledgered optional so the grader prices holding. · news |
| ASML | ASML Holding NV | 1859.86 | HOLD | 1859.86 | 1751.05 | 1944.05 (+4.5%) | 2140.50 (+15.1%) | 2026.37 (+9.0%) | ASML eased to HOLD 73 (-0.40%) and stays above cost (+1.80%) ahead of its 10-14 Q print. PROFIT_ARMED is the U4 phantom (Gain_ATR 0.75, T12 ratio) with no ticks. The stop is held loose at 1,751.05 into the binary event (P2/USC-EOQ-CH); the engine's 1,790.34 is not adopted. W1: any SELL/STRONG SELL - REDUCE print or a settled close < 1,751.05 -> full exit (, T5 stub). |
| — | Advanced Micro Devices, Inc | — | NO ACTION | — | — | n/a | n/a | n/a | AMD printed BUY 64 PullbackBuy_VWAP (the book's preferred family, L1) from WATCH 38, and it passes the quality gate. val_adj is suppressed to 0 because the DCF is a broken anchor (P/note B: vs), but adj 64 < 65, it is a single print (Q4), and the limit is 2.66 ATR below the close. Re-arm (S4): a 2nd consecutive bullish print with raw cv >= 65 -> QUEUE a GTC limit at the live Entry_Price (tonight 574.31), ~35% portion x 0.5 size modulator; stop/R:R checked then (tonight 1.17 ATR, 1.69:1). |
| — | ASE Technology Holding | — | NO ACTION | — | — | n/a | n/a | n/a | ASE upgraded to STRONG BUY 81 (Buy_Rank 1, two consecutive bullish prints), adj 71, but it fails the hard quality gate (F-Score/FCF screen), which blocks new entries; the limit is also 3.04 ATR below the close. No re-arm while Quality_Pass is False (Q5). |
| — | Tesla Inc | — | NO ACTION | — | — | n/a | n/a | n/a | Tesla flipped NO TRADE -> BUY 76 on a FailedBreakdown_Up_20D: a single print (Q4), a chase family that is/ stop-first here (USC-3, cell -7), adj 59, and it fails the quality gate. Its own 12wk 374.94 is below the 378.73 entry (S7). |
| — | Intel Corporation | — | NO ACTION | — | — | n/a | n/a | n/a | Intel faded BUY (-2.63%) and still fails the quality gate; adj 54. No re-arm while Quality_Pass is False. |
| — | Lumentum Holdings | — | NO ACTION | — | — | n/a | n/a | n/a | Lumentum printed BUY - ANTICIPATE 63, 2 of the last prints, so the anticipate slot's count and conviction floor are met, but the hard quality gate fails (W) and the stop is 3.0 ATR / -18% wide (S). No re-arm while Quality_Pass is False. |
Outcome & track record
Accuracy at the time of this record.
63 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 →
0.493 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.