Recommendations
0 to acquire · 2 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 |
|---|---|---|---|---|---|---|---|---|---|
| AMD | Advanced Micro Devices | 454.62 | SELL ALL | 454.62 | 475.00⚠ | 456.30 (+0.4%) | 460.21 (+1.2%) | 514.61 (+13.2%) | Exit AMD in full. The stop line the prior verdict committed to in writing - a close below 475.00 completes the exit - has now been hit decisively: AMD fell 8.15% to 454.62, which is 4.29% and roughly half an ATR below that trail, versus the marginal 0.14 ATR nick that was correctly held a week ago. Price also closed below its 50-day average for the first time in this decline, and the signal reprinted a bearish RallySell_BearTrend AVOID for a second straight session, leaving the position 11.9% underwater. News confirms the character of the move rather than contradicting it: AI chip names fell hard on renewed questions about whether AI capital spending can earn its return, with AMD's 150x trailing earnings multiple singled out and the selling described as forced and leveraged - a continuation mechanic, not a washout. AMD's own business case (the MI-series ramp) is intact and the model's 12-week view of 514.61 is still 13% above today's price, so this exit gives up modelled upside; it is taken because a written stop trigger fired and this book's record on re-arguing fired triggers is poor. OPERATIONAL: supersedes and escalates the 07-27 30% trim that never filled - the auto-executor has not run since 2026-07-18, so faithful execution of the committed sequence is the whole 172, not a re-queued 52. Learnings applied: L2/L3 (execute the written de-risk promptly), L8 (fills at the next open; reprice if the open gaps >~1.5%), USC-5 (broken technical -> de-risk to the technical's own tier; do not hold an oversized loser into a binary print). Catalyst noted and overruled: AMD Q2 earnings 08-04 AMC is 5 sessions out, inside the catalyst-aware-hold window, but that doctrine names a decisive stop break as its own exception and protects winners, not a -11.9% position. Gates: G1 n/a (not a fresh breakout at cv>=80); G3 does not block (family is bearish); G2 suppresses the valuation amplify on a broken 175.40 DCF anchor, so MoS_FV -17.14 gives no tier bump and the exit is purely signal-based. Not armed (Gain_ATR -1.48) - loss-control, not a profit-take, so the never-100%-from-a-profit-take cap does not apply. Estimates use f=0.30 per L5 (calib_1w -0.548 degenerate). Note the bearish-family artifact: printed Stop_Price 493.48 and Target_Price 460.21 both sit ABOVE the 454.62 close and must not be adopted as levels. Realized -vs the 516.075 cost. Re-entry trigger: a PullbackBuy_VWAP or ReversalUp_Oversold print with conviction >= 70 AND a reclaim of EMA50 (~489); do not re-enter on the earnings gap itself (L6). · news |
| TSM | Taiwan Semiconductor (ADR) | 392.31 | SELL ALL | 392.31 | 375.56 | n/a | n/a | 346.32 (-11.7%) | Exit Taiwan Semiconductor in full - completing the exit the prior verdict already decided but which never reached the market. The technical case has only deteriorated: the stock printed no-trade with zero conviction for a fourth consecutive session, the 12-week view has slid again to 346.32 (11.7% below the 392.31 close, deepening from -8.9%), and the loss of the 100-day average is now confirmed on top of the 20- and 50-day, leaving the 200-day at 362.93 as the last structural support 7.5% below. The position is 10.4% underwater and traded as low as 383.03 intraday. TSMC's fundamentals remain the strongest in the book - record Q2 revenue of, a 2026 guide raised past 40% growth, and a fresh US manufacturing commitment - and that is the honest counter-case; but those facts are three weeks priced, they were equally true when the trigger first fired, and constructive fundamentals do not override a technical trigger that has now fired four times. News is neutral with no fresh catalyst to demote the exit. OPERATIONAL: supersedes the 07-27 full-exit card that never filled (auto-executor last ran 2026-07-18); the delay alone cost roughly 1.70% (on) as the price slid 399..31. Learnings applied: L3 (execute the de-risk promptly - this is now its third session of slippage), L4 (settled close authoritative), L8 (fills at the next open; reprice if the open gaps >~1.5%), USC-5 (a bullish fundamental story is not a reason to keep an oversized position through a broken technical). Valuation is amplify-only and suppressed here by G2 - the 45.28 DCF anchor is a broken artifact - so MoS_FV -14.19 contributes no tier bump and does not originate the sell. PROFIT_ARMED prints for the fourteenth consecutive session and is again a FALSE ARM (Gain_ATR -2.81, T12_Progress_Pct 113.28 on a loss): this is loss-control, not an ADR-0012 profit-take. No 1wk or 4wk estimate is derivable because a no-trade row prints no Target_Price. Realized -vs the 438.02 cost (-book-to-date on TSM). Re-entry trigger: a bullish-family print (not NoTrade) with conviction >= 65 AND a reclaim of EMA100 (~399). · news |
| GLW | Corning Incorporated | 126.01 | WATCH | 126.01 | 86.79 | 138.39 (+9.8%) | 167.28 (+32.8%) | 71.83 (-43.0%) | Passed on Corning despite it being the day's only buy signal and the top-ranked one. The technical read is a reversal-from-oversold at high conviction, but the case against it is overwhelming: the stock has just gapped down on its Q2 report - revenue and earnings beat, but the third-quarter guide came in light and growth in the optical-communications business decelerated from 81% to 36% to 32% year over year - and it now sits roughly 55% below where it traded a month ago, with analysts openly re-rating it as an ex-supplier story. Buying a fresh post-earnings dislocation with a structural growth question attached is a falling knife, not a reversal. On top of that the company fails the quality screen outright (weak free-cash-flow yield and returns on capital, the worst quality rank in this book), which blocks any new position on its own, and it screens expensive on intrinsic value even after the crash. OPERATIONAL: four independent strikes - (1) hard quality gate Quality_Pass=False blocks a new entry; USC-3 forbids overriding the gate for a chase-family buy; (2) val_adj -10 from MoS_FV -9.27, and G2 does NOT suppress it (GLW is a ~1% TTM revenue grower with a usable 52.49 DCF anchor, not a broken hyper-growth artifact), taking conviction 82 -> adj 72 - above the 65 floor, so the gate rather than the floor is what kills it; (3) news OVERRIDES per Step 6-7; (4) the row is internally contradictory - a bullish BUY carrying Target_12Week 71.83, i.e. -43.0% below the 126.01 close, against a +32.8% 4wk Target_Price, with a stop 31.1% (2.56 ATR) away (systemic finding #6). Logged as a graded pass so the counterfactual layer prices the no-chase decision. Re-arm trigger: a PullbackBuy_VWAP print (L1) with the quality gate passing and Target_12Week turning positive. · news |
Outcome & track record
Accuracy at the time of this record.
8 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 →
-0.548 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.