Recommendations
0 to acquire · 1 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 |
|---|---|---|---|---|---|---|---|---|---|
| TSM | Taiwan Semiconductor Manufacturing | 403.31 | SELL ALL | — | 406.37⚠ | n/a | n/a | 341.79 | Completing the exit of a residual TSMC stake that has traded below its stop for six straight sessions with no directional signal from the model and a twelve-week projection still 15% under the current price. Yesterday's violent AI-hardware rebound (TSMC +7.65% on Microsoft's 43% Azure growth) is taken as a materially better exit price rather than a new thesis - the business case for TSMC was never in question, but this position's own risk line was broken and never repaired. OPERATIONAL: 5th arming of an exit unfilled since 07-25 (executor stall) - UT-11 re-fire, not a re-litigation. L2 leg-2 (12wk 341.79 = -15.25%) holds; leg-1 (stop break) has narrowed -7.80% -> -0.75% (0.15 ATR) and is no longer decisive - stated openly, exit retained on the residual/incomplete-exit basis plus close below EMA20 412.41 and EMA50 415.30. G2 suppresses the valuation amplify (DCF vs, broken ADR scaling, 13th session). PROFIT_ARMED at T12_Progress 118.0 on a -7.92% position is the UT-9 arm-on-loss mislabel, inert. Better fill vs the 07-30 ref: +on; proceeds, realized ~-. WITHDRAWAL TRIGGER: two consecutive settled closes above 406.37 with a rising 12wk cancels this exit and re-bases the residual as a fresh position. News is a bullish counter-signal weighed and not overriding. L2/L3/L4/L5/L8, UT-9/UT-11 applied. · news |
| SNOW | Snowflake Inc. | 298.10 | NO ACTION | 294.19 | 253.53 | 318.58 (+8.3%) | 375.50 (+27.6%) | 424.79 (+44.4%) | Standing aside on Snowflake despite a fresh 52-week high, because the quality screen fails outright: earnings power measured on current profitability is negative, the fundamental strength score is mid-pack, and the company ranks 23rd of 26 in this book on quality. The entire investment case rests on a long-dated growth projection rather than cash the business generates today, and the shares already trade above our estimate of intrinsic worth. Momentum and the AWS partnership are real; they are not a substitute for the balance-sheet test. OPERATIONAL: hard Quality_Pass gate FALSE (F-Score 5, EPV -/sh, rank 23/26) - 7th consecutive session blocked; independently below the floor at adj 57 (65 conv - 8 val_adj on MoS -1.66, bias 0). Telling divergence: price +5.4% to a new high while conviction collapsed, so the engine de-rated the setup as it extended - the 'best-formed setup in the book' argument no longer holds on its own terms. L1 breakout-family discount also applies. Untaken @ 294.19 buy-stop (size mod 0.75). Estimates at f=0.30: 1wk 318.58, 4wk 375.50, 12wk 424.79 - the 12wk exceeds the DCF anchor (projection assumes growth beyond priced-in). · news |
| AAPL | Apple | 333.43 | NO ACTION | 323.85 | 315.87 | 327.41 (+1.1%) | 335.72 (+3.7%) | 404.07 (+24.8%) | Passing on Apple for a second session, by the narrowest margin. The setup is the kind this book likes - a pullback toward the average trading price inside an uptrend - but the shares still trade well above what the cash flows justify, which docks the score just under our buy threshold. Thursday night's results were strong at the headline (record June quarter, revenue 4bn +16%, iPhone +22%, earnings vs expected) yet soft where the multiple lives: services and Greater China both missed, and management is absorbing a worldwide memory and processor shortage that is already forcing Mac and iPad price rises. The stock fell 3-4% after hours, which walks it back toward our buy level rather than away - worth another look once the reaction settles. OPERATIONAL: adj 63 vs the 65 floor (73 conv, val_adj -10 on MoS -3.26, bias 0) - second session missing by exactly two. L4: the after-hours ~325.91 print (+0.6% above the 323.85 buy-limit) is not a settled close and does not re-rate conviction; L6 forbids trading the print reaction. RE-ARM at the next EOD on the settled 07-31 close at the then-live Entry_Price, require adj >= 65, no gap-chase. Untaken @ 323.85 (size mod 0.5). Estimates at f=0.30: 1wk 327.41, 4wk 335.72, 12wk 404.07 - the 12wk exceeds the DCF anchor. · news |
Outcome & track record
Accuracy at the time of this record.
9 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 →
0.134 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.
24 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.