Recommendations
1 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 |
|---|---|---|---|---|---|---|---|---|---|
| AAOI | Applied Optoelectronics, Inc. | 150.28 | BUY — QUEUED @150.03 | 150.03 | 106.06 | 161.81 (+7.9%) | 237.96 (+58.6%) | 148.34 (-1.1%) | Applied Optoelectronics is the physical layer of the AI data centre, and this quarter it stopped being a promise: record Q2 revenue of (+86% year-on-year), the first return to non-GAAP profitability, and a Q3 guide of -290M that implies 130% growth, with management saying manufacturing capacity - not customer demand - is what limits them through mid-2027. First 1.6T qualification with a major hyperscaler completes within weeks and a + order ships from late Q3. We buy it on a fresh 20-day breakout, but on a limit rather than at the close, because the shares rose 15.5% in a single session and trade 25% above their volume-weighted average - we want the position at our price, not the crowd's. Half the normal size: the company is still unprofitable on a statutory basis, the stock has already trebled this year, and our own valuation model cannot put a positive intrinsic value on it. OPERATIONAL: L1/UT-6 no-chase - GTC limit at the model Entry_Price 150.03, entry range 145.71-154.35, unfilled on a gap-up by design; expires 2026-08-19 (3 sessions), withdraw or reprice at each EOD. L6 checked and NOT applicable (Q2 print was 2026-08-06, eight sessions prior). Size modulator 0.5x applied by stated assumption: Val_Signal NA arises from a NEGATIVE FV_per_share (-3.38) with F_Score 4, read as the MoS_FV<=-3 tier rather than neutral 1.0x; full would have been (10.1% of, 3.0% at defined risk). Sizing arithmetic: 50.71% x x 20% x 0.50 = / 150.03 = = (5.07% of); defined risk = 1.49% of. WARNING: Target_12Week 148.34 sits BELOW the action price while Target_4W is +58.6% - treat as a 1-4 week trade on a hard chandelier trail at 106.06, not a hold. All four graded buy families are 0-for-8 on 4-week targets. Scorecard bias 0 (no actionable cell, UT-8); f=0.134. · news |
| NBIS | Nebius Group, N.V. | 277.68 | BUY-STOP | 278.76 | 194.78 | 301.27 (+8.1%) | 446.73 (+60.3%) | 364.17 (+30.6%) | Nebius delivered an extraordinary quarter - revenue up 454% to, of adjusted profit and a $3bn annualised run-rate - and the market repriced it 34% higher in a single session. We are standing aside, not because the business disappointed, but because we would be paying up 44% above where the shares traded before the results, into a company that is still consuming cash to build data centres, and while an unresolved question hangs over whether its largest customer will build its own cloud instead. Good company, wrong entry. OPERATIONAL: three independent blocks, any one sufficient - (1) quality gate hard-blocks new entries, Quality_Pass False, F_Score 6, FCF screen failed; (2) L6 post-earnings gap chase, +43.7% off the pre-print close in three sessions, buy-stop would sit at 278.76 vs a 193.23 pre-print close; (3) standing overlay override 'NO adds until the Meta question clears', uninvalidated (the 08-14 Nvidia financing headline does not address it). Reinforcing only: own-book anticipate counterfactual n=4 median 4wk -8.81%. Confirmed 3-of-3 ANTICIPATE prints at cv 78/75/88 and BofA PT raised, so ledgered direction:none for counterfactual grading of the stand-down. · news |
| LITE | Lumentum Holdings | 926.14 | NO ACTION | 926.14 | 882.44 | 949.55 (+2.5%) | 1100.94 (+18.9%) | 1052.86 (+13.7%) | Lumentum rides the same AI-optics wave we are buying through Applied Optoelectronics, and it carried the highest signal conviction on the board. We passed because the shares are the most expensive thing in this portfolio on any measure of what the business is actually worth, and the company fails our financial-quality screen - a combination we do not fund with new money when a cleaner way to own the same theme exists. OPERATIONAL: cleared the adjusted floor at 66 (cv76, Buy_Rank 1) but blocked by the hard quality gate (Quality_Pass False). MoS_FV -36.38 (uncapped val_adj would be -182; capped at -10), FV/share 24.78 vs a 926.14 close. Theme expressed via AAOI instead - the only optics name whose valuation gate is OFF (NA) rather than failed. Ledgered direction:none for counterfactual grading. |
| MU | Micron Technology, Inc. | 971.66 | NO ACTION | 971.66 | 942.08 | 987.51 (+1.6%) | 1089.98 (+12.2%) | 1018.97 (+4.9%) | Micron is the best-quality candidate on the board - top-tier financial-strength score, the memory cycle running hot, and the first genuine buy signal after three flat sessions - and it missed our threshold by two points. The only thing holding it back is price: the shares already discount a great deal of the coming upcycle. We are watching it closely and a modest pullback, or one more point of signal strength, brings it into the portfolio. OPERATIONAL: adj 63 vs the 65 floor - closest near-miss of the run. cv69, Buy_Rank 4, Quality_Pass True, F_Score 8. Killed purely by val_adj -6 (MoS_FV -1.25). Standing overlay override 'hold conviction upgraded, add only on signal' now HAS its signal but the arithmetic still fails. WATCH for the re-arm. Ledgered direction:none for counterfactual grading. |
| DELL | Dell Technologies Inc | 490.81 | HOLD | 490.81 | 454.65 | n/a | 550.16 (+12.1%) | 699.40 (+42.5%) | Dell has become an artificial-intelligence infrastructure company wearing a personal-computer company's name: server revenue up more than sevenfold year-on-year, roughly $60bn of AI systems guided for the coming year, and a share price that crossed for the first time this week. We are holding all and raising the protective stop to to lock in more of a 6.4% gain rather than trimming into strength - the twelve-week view is still 42% above today's price, and cutting a winner because it has gone up is how portfolios underperform. OPERATIONAL: no sell origination available. NOT profit-armed (Gain_ATR 0.99 vs 3.0 floor; T12_Progress 70.18% vs 90% floor) so ADR-0012 cannot fire; conviction is -17, short of the -20 tick; Exit_Warning blank; L2 fails both legs (close far above stop, Target_12Week 699.40 = +42.5%); G3 forward-view gate would block a trim regardless. TRAIL-RAISE 444.14 -> 454.65 = chandelier 2.0 x ATR (29.67) below the 514.00 all-time high. The engine's printed Stop_Price 475.97 is REJECTED as too tight - 0.50 ATR below the close on a 6.0%-ATR name, inside one session's range (see systemic finding 4: engine stop went 444.14 -> 386.73 -> 475.97 in three sessions on family transitions alone). ADR-0020: new stop exceeds the prior peak_stop 444.14, so the watermark REBASES to 454.65 and trail_erosion_pct resets 12.93% -> 0.00%; no Trail Erosion fire. Second consecutive fade off the ATH (514.00 -> 494.51 -> 490.81) flagged, not a sell basis. · news |
| NVDA | NVIDIA Corporation | 225.16 | HOLD | 226.80 | 206.05 | n/a | 265.16 (+16.9%) | 254.69 (+12.3%) | We bought Nvidia one session ago and are holding it into results on 26 August. The signal has gone quiet - momentum stalled even as the trend stays intact - but the position is barely a quarter of a percent underwater, sits 9% above its protective stop, and the twelve-week view remains 13% higher. Nothing here justifies selling. This week Nvidia unveiled a financing programme with Apollo, BlackRock, Blackstone, Brookfield, Goldman Sachs and KKR designed to mobilise over $500bn so its customers can afford to buy more of its hardware; UBS expects the coming quarter to beat guidance by several billion dollars. We hold through the print. OPERATIONAL: entry filled from the 08-14 anticipate queue at 226.80 (buy-stop 225.76, +0.46% slippage, txn ustech-20260815-0001). Conviction collapsed (NoTrade: 'Consensus conflict + low conviction', pillars Trend Bullish/84 vs Momentum Bearish/17) but fires NOTHING: ADR-0012 tick (b) requires an ARMED position and Gain_ATR is -0.28 (underwater), with UT-9 independently ruling arm-on-loss inert. L2 fails both legs. STOP SET at 206.05 - first stop this position has carried, closes the monitor no_stop warning. Catalyst-aware hold through 2026-08-26; do not pre-trim. NOTE: the anchor CSV prints Held=N / for NVDA because the scan wrote at 06:00:18 and the executor booked at 06:00:38 - read from input/ustechportfolio.json per UT-7 (systemic finding 3). Watch: a 2nd consecutive NO TRADE would satisfy tick (d) if the position ever arms. · news |
Outcome & track record
Accuracy at the time of this record.
15 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.
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.