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 |
|---|---|---|---|---|---|---|---|---|---|
| AAOI | Applied Optoelectronics, Inc. | 113.15 | SELL ALL | 113.15 | 111.93 | n/a | n/a | 83.05 (-26.6%) | Closing the book's worst position outright. Applied Optoelectronics broke its risk line decisively on Monday after disclosing a at-the-market offering, and although Tuesday's analyst upgrade produced a 5% bounce, that bounce came on 45% of the selloff's volume and reclaimed the stop by only a tenth of a day's trading range. The underlying picture has not healed: our own 12-week view has now sat below the share price for six straight sessions and has fallen to -27%, the stock trades below its 20-, 50- and 100-day averages and 10% under its volume-weighted average price, and the pillar consensus has turned outright bearish. The company's growth story is real - record revenue, a credible 800G/1.6T capacity ramp, demand outpacing supply into mid-2027 - but it is being funded by roughly $1bn of cumulative share issuance that mechanically sells into every rally, and the business is still lossmaking with negative free cash flow, ranking 28th of 31 on our quality screen. We take the better exit price the delay handed us and step out. || OPERATIONAL: 4th re-fire of the 08-25 MOO exit (executor 6 sessions stale, last_run_date 2026-08-18); realized -vs cost 150.03, better than the 08-25 ref of 107.63. L2 origination: stop leg now AT the line (113.15 vs 111.93 = +1.09% = 0.08 ATR) after a decisive -3.84% break, dead-12wk leg 6th session (135.97->116.18->120.41->112.17->84.20->83.05), signal leg AVOID cv59 on a bearish family with Exit_Strategy 'immediate'. val_adj 0 (Val_Signal NA, negative EPV -3.38, DCF blank, Quality_Pass False, F 4, Quality_Rank 28/31) - 100% signal-originated. UT-9 12th session: PROFIT_ARMED INERT (Gain_ATR -2.43 on -24.58%); T12_Progress_Pct 136.24 is the arm-on-loss mislabel worsening. ADR-0020 did not fire (peak_stop = live stop 111.93, 0% erosion). 1wk/4wk n/a (AVOID row prints no Target_Price); band Est_Low 88.34 / Est_High 144.99 = -21.9%/+28.1%. FALSIFIER: a decisive close back above EMA20 124.08 with T12 turning positive repairs the basis and it re-enters as a FRESH buy candidate, which must then clear the quality gate it currently fails. · news |
| NVDA | NVIDIA Corporation | 213.05 | HOLD | 213.05 | 206.05 | 214.18 (+0.5%) | 224.77 (+5.5%) | 219.56 (+3.1%) | Holding through tonight's earnings rather than trimming into them. Nvidia reports Q2 after the close on 26 August, and our rule into a known catalyst is to hold and trail unless the position is already breaking down - it is not. The shares rose 2.2% to sit right on their volume-weighted average price and above their 50-, 100- and 200-day averages, conviction improved ten points onto a bullish signal, and the 12-week view remains positive. The setup is genuinely two-sided: analysts expect of earnings on about $92bn of revenue against company guidance of $91bn, so estimates sit above the guide - the configuration that punishes an in-line result - while commentary on China, which guidance excludes entirely, is the swing factor in either direction. The position is small enough that we can simply let the event happen: it is 3.7% of the book with of money at risk to the stop. || OPERATIONAL: catalyst-aware hold, ZERO sessions out; horizon stance hold-through, band -8%/+9% = -, confidence high. Execution at the 08-26 open is PRE-print. No exit basis on any origination class: close +3.40% above the 206.05 stop (improved from +1.18%), T12 219.56 = +3.06% positive, no SELL label, no confirmed lower high. L6: no add after a gap either. NO TRAIL-RAISE - chandelier 2.0xATR (5.859) below the 214.729 high = 203.01, lower than 206.05, ratchet rejects; engine Stop_Price 201.33 lower still. 206.05 HOLDS and sits INSIDE the implied band (band low 196.01), 3.29% below close - a meaningfully adverse reaction stops this out at the 08-27 open, which is deliberate and affordable at 0.12% of. UT-9 12th session: PROFIT_ARMED INERT (Gain_ATR -2.35 on -6.06%). ADR-0020 erosion 0% (peak_stop = live stop). NOTE systemic finding 7-bis: the model's own 1wk band (Est_Low 208.79 / Est_High 226.23 = -2.00%/+6.19%) is EVENT-BLIND, far narrower than the horizon band - do not read the Est_* range as risk-complete tonight. REVISIT at the 08-27 EOD with the print in hand. · news |
| LITE | Lumentum Holdings | 885.57 | NO ACTION | 885.57 | 841.10 | 900.01 (+1.6%) | 1036.02 (+17.0%) | 965.87 (+9.1%) | Passing on the strongest buy signal this book has printed since inception, because the company fails our fundamental quality screen. Lumentum jumped 6.7% and the model's conviction hit 79 - the highest reading in twelve weeks and comfortably clear of our threshold even after the maximum valuation penalty. But the shares change hands at roughly 34x their assessed intrinsic value, generate free cash flow of 0.15% and earnings of 0.39% against an share price, and rank 22nd of 31 on quality. The AI-optics demand story is real and accelerating, yet a meaningful part of this specific move is mechanical - Nasdaq-100 inclusion and momentum-ETF re-weightings, with MSCI's August review effective 31 August - and the same coverage flags heavy passive-flow dependence, insider selling and customer concentration. Buying a 6.7% index-flow move at market, in a signal family our own record tells us to discount, is a chase. Logged so the cost of this pass can be measured. || OPERATIONAL: ledgered as a direction:none counterfactual per ACTIVE learnings advisory (d)(iii) - price what the F-Score/FCF quality gate costs before re-evaluating it. cv 79 + val_adj -10 = adj 69, CLEARS the 65 floor; blocked solely by Quality_Pass False (F 6, Quality_Rank 22.5/31, FCF_Yield 0.149%, Earn_Yield 0.388%). MoS_FV -32.505 (FV/sh 24.78 vs price 830.17) = maximum -10 haircut, deepest in the book ex-SPCX. Two independent secondary objections: signal family FailedBreakdown_Up_20D is on L1/UT-12's discount list, and Entry_Distance_ATR 0.0 means entry == close, i.e. a market chase of a +6.67% session. This is systemic finding 8's cleanest test case to date and it argues FOR the gate on this occasion. · news |
Outcome & track record
Accuracy at the time of this record.
22 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 →
0.096 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.
53 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.