Recommendations
1 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. | 103.39 | SELL ALL | 103.39 | 111.93⚠ | n/a | n/a | 58.93 (-43.0%) | We are selling the entire Applied Optoelectronics holding at the open and taking the loss. The shares have now closed below both our risk line and their long-term trend for a second day running, the model's twelve-week view has collapsed to 43% below today's price, and the company is its expansion by selling of new shares straight into a falling market on top of already raised - open-ended dilution that puts a permanent seller above the price. The underlying business is genuinely booming (revenue up 86% year on year), but a fast-growing company issuing equity into weakness is still the wrong thing to own here. OPERATIONAL: 8th re-fire of the exit first raised 2026-08-25; escalated to MARKET-ON-OPEN per UT-3 (an L2/L3 exit still unexecuted at the next EOD escalates rather than being re-recommended). Engine flipped AVOID 47 (x3) -> STRONG SELL - REDUCE cv62, Sell_Rank #1; its own Action_Rationale reads 'REDUCE 90% (target full exit)', so the card takes 100%. Basis: recorded stop 111.93 broken -7.63% (from -5.09%), 2nd close below EMA200 (103.39 vs 106.43), Target_12Week 58.93 = -43.00% and falling (66.96 -> 58.93 in two sessions). L2 + L3 + UT-3. UT-9: the row's PROFIT_ARMED print is INERT - Gain_ATR -5.09, position -31.09% underwater; arm-on-loss mislabel, plays no part in this decision. Valuation blind: Val_Signal NA, FV_per_share -3.38 (negative intrinsic), val_adj 0, no tier bump. Scorecard caution stated not hidden: RallySell_BearTrend|sell is n=2 at hit_1w 0.00 / hit_4w 0.00 - below the actionable floor so no bias applied, but this exit may look early. Estimates: 1wk/4wk n/a (bearish exit row emits no Target_Price - nothing to interpolate, not invented); 12wk 58.93 is the downside stepped out of. Model band 88.85-122.05. Realized - (-31.09%) vs 150.03 cost; proceeds = 3.73% of equity. Executor note: the 09-01 executor run filled the CRM buy from the same 08-29 verdict and skipped THIS sell. · news |
| AAPL | Apple | 325.13 | BUY-STOP — QUEUED @323.17 | 323.17 | 299.10 | 327.79 (+1.4%) | 371.31 (+14.9%) | 332.66 (+2.9%) | We are placing a small buy order in Apple that only triggers if the shares keep rising. Apple was one of just three stocks in the book to close higher on a day when twenty-seven fell, on the day John Ternus formally took over as chief executive, and it is the only high-quality name in the portfolio currently showing a genuine buy setup. His first public outing is the iPhone 18 Pro and first foldable iPhone launch on 9 September, five trading days away. We are deliberately buying only half our normal amount, because analysts' average price target is essentially where the stock already trades - the setup is good, the starting price is not cheap. OPERATIONAL: ANTICIPATE slot (4th slot, one per book, NOT one of the <=3 ACQUIRE). Eligibility satisfied on the letter of the rule - last three snapshots BUY-ANTICIPATE 83 -> WATCH 55 -> BUY-ANTICIPATE 83 =; conviction 83 well above the 55 slot floor; the 08-29 card pre-committed to exactly this trigger. Quality_Pass TRUE, Quality_Rank 3/31 - clears the gate that blocked SNOW/SAP/MSFT. Entry: GTC buy-stop @323.17, entry range 321.17-325.18 (+/- 0.25 x ATR 8.02). Close 325.13 sits ABOVE the stop (Entry_Distance_ATR -0.24, inside the -0.25 no-chase bar) so it should fill at/near the 09-02 open. RSI 61.1, VWAP_Distance +4.47% - not extended. Trend 94 / Mom 50 / Vol 33, Consolidation_Bullish. Sizing: Portion 50.00% x equity x buy_pct_of_portfolio 20% =; x0.75 size modulator (MoS_FV -2.975 in the -3<MoS<=-1 band, from the REGENERATED fairvalue file); x0.5 anticipate-slot factor =; / 323.17 = 110.07 -> = = 3.75% of equity. max_position_pct 60% and both non-binding. Stop 299.10 = -7.45% / ~3.0 ATR; risk = 0.28% of equity. Estimates f=0.096 (Step 7 fallback - CSV has only a single Est_Low/High band, no ADR-0013 Est_*_Point columns). 12wk 332.66 EXCEEDS DCF anchor 237.39 - projection assumes growth beyond priced-in. WARNING - forward-curve inversion: 4wk 371.31 sits ABOVE 12wk 332.66; the model expects the move given back. Counterfactual argues against and is why size is halved: anticipate n=8, median 1wk -0.73% / 4wk -8.81% ['saved']. Scorecard cell AnticipationUp_VCP|buy n=1 hit_1w 0.00 - report-only, no bias. Catalyst: 09-09 event is 5 trading sessions out (09-07 Labor Day holiday) - ON the <=5-day boundary. expires_on 2026-09-08 = anchor + 3 trading sessions. · news |
| DELL | Dell Technologies Inc | 425.00 | HOLD | 425.00 | 412.30 | 429.88 (+1.1%) | 475.82 (+12.0%) | 507.97 (+19.5%) | We are keeping the Dell holding whole and cancelling the sell signal our own risk line generated. Dell closed 6.8% lower ahead of its results, which nudged it just below our stop - but the results came out after that close and were exceptional: revenue and profit far ahead of expectations, a record 9bn of AI server orders, a $95bn order backlog, and full-year profit guidance raised by more than 40%. The shares rose 8-10% in after-hours trading. Selling into that would have been acting on a price that no longer exists. We are moving the risk line down to the model's own level and will reset it properly once the post-results price settles. OPERATIONAL: STOP BREACH CANCELLED - PHANTOM. Close 425.00 vs recorded stop 427.70 = -0.63% = 0.11 ATR (ATR 25.41), NOT decisive per CLAUDE.md 9. L2 not satisfied: L2 requires stop-break AND negative 12wk; Target_12Week 507.97 = +19.52%, firmly positive. Engine prints HOLD cv53, no Exit_Warning. NEWS OVERRIDE: DELL reported FQ2 FY27 after the 09-01 close (THE ANCHOR SESSION) - revenue 97bn vs 92bn exp, adj EPS vs (+43% beat), GAAP EPS (+273% YoY), record 9bn AI-server orders, $95bn backlog, FY27 revenue guide raised ~$25bn to ~$192bn, AI-server guide to $74bn, FY adj EPS guide ->, Q3 guide $49bn/vs 42bn/consensus; +8-10% after hours. STOP RESET 427.70 -> 412.30 (the scan's live Stop_Price, -2.99% / 0.5 ATR). The 427.70 level was deliberately held on 08-29 'through the 2026-09-03 FQ2'; the calendar was TWO SESSIONS WRONG - earnings landed 09-01 after the close. Honouring 427.70 at the 09-02 open would have sold (, 31.95% of equity) into an earnings gap-up. Will be re-based off the settled post-gap close at the next EOD. NO ADD either - L6 (no post-earnings gap-chase) and UT-1 (MU +14% AH round-trip) govern; DELL is not in the buy pool (Action HOLD). Position: 713 @ 461.298 cost, - (-7.87%) at the 425.00 mark. DCF_per_share 485.61 is ABOVE the current price - the only holding of which that is true. Estimates f=0.096; 12wk 507.97 marginally exceeds the 485.61 DCF anchor. SYSTEMIC: decisions/ustech_horizon.json does not exist; the us_horizon.json parent fallback contains NO DELL coverage at all - this book needs its own horizon generation. · news |
| NVDA | NVIDIA Corporation | 217.44 | HOLD | 217.44 | 213.25 | 218.97 (+0.7%) | 233.35 (+7.3%) | 229.42 (+5.5%) | We are holding Nvidia unchanged and leaving its stop where it is. The scan again labels the position as 'profit armed', but the holding is 4% underwater - you cannot take profits on a loss, so that label is ignored for a second run. Nothing has actually deteriorated: conviction eased only slightly, the twelve-week view is still 5.5% above today's price, and there is no exit warning on the row. OPERATIONAL: UT-9 - PROFIT_ARMED (T12_Progress 94.78 >= 90) is INERT on an underwater name (Gain_ATR -1.18, -4.13%). All four ADR-0012 fire ticks checked and NONE fires: (a) no other Exit_Warning code on the row; (b) conviction = -7, not the >=20 collapse; (c) Target_12Week 229.42 vs 1.02 x close 221.79 - NOT dead; (d) HOLD, not 2 consecutive NO TRADE. No trim AND no trail-raise, because the arming that would mandate a trail-raise is itself the mislabel. STOP DELIBERATELY UNCHANGED at 213.25 - only 0.53 ATR below the 217.44 close, the tightest line in the book and tight enough to whipsaw. NOT loosened to the scan's 201.53: lowering a stop on an underwater position is a discretionary increase in risk with no new information to justify it (the ratchet only moves up). Flagged as a live fragility. = = 3.85% of equity, unrealized -vs 226.80 cost. Estimates f=0.096; 12wk 229.42 exceeds DCF anchor 163.98. |
| CRM | SalesForce Inc | 258.11 | HOLD | 258.11 | 251.77 | 260.54 (+0.9%) | 283.46 (+9.8%) | 367.81 (+42.5%) | Our Salesforce order filled on 1 September at exactly the price we set, and we are holding it with a much tighter risk line. The company's AI business is now a 9bn recurring revenue line growing over 200% a year, full-year guidance was raised, and its Claude partnership is now shipping into Slack. The shares have run 22% in a week and are technically overbought, so rather than buy more we are lifting the stop close under the price to protect the position. Investor Day at Dreamforce on 16 September is the next scheduled event. OPERATIONAL: FILL CONFIRMED - the 08-29 GTC buy-stop executed @257.66 on 2026-09-01 (txn ustech-20260901-0001); cash 573,502.79 -> 508,572.47. Marked 258.11 = + (+0.17%). CRM was one of only three green prints in a 3-up/27-down session (+0.22%). STOP RAISED 211.73 -> 251.77 (the scan's live Stop_Price, -2.46% / 0.5 ATR). The 211.73 placeholder was a -17.8% chandelier sized for a post-gap ENTRY - correct as an invalidation level before the fill, an unnecessary risk on a filled position. Signal cooled STRONG BUY 89 -> BUY 62 -> HOLD 60 but carries NO Exit_Warning; Target_12Week 367.81 = +42.50%. RSI 81.2 is the caution and is the reason the stop moves up rather than the position being added to. Valuation MoS -3.373 on the regenerated file (crosses the <=-3 tier that was hand-derived last run) - held name, so amplify-only and nothing to amplify absent a sell signal. Estimates f=0.096; 12wk 367.81 marginally exceeds DCF anchor 360.92. Forward catalyst: Dreamforce Investor Day 2026-09-16, outside the <=5-day window. · news |
| SAP | SAP AE | 212.04 | NO ACTION | 209.73 | 203.16 | 210.66 (+0.4%) | 219.49 (+4.7%) | 293.65 (+40.0%) | SAP was the closest thing to a buy today - a clean pullback entry just below the price, and the least expensive-looking name in the whole book - but it fails our financial-quality screen, which blocks new positions. Recorded and not acted on so we can measure later whether that screen is helping or costing us. OPERATIONAL: THE NEAR-MISS OF THE RUN. adj 65 lands EXACTLY ON the floor and the quality gate is the only thing in front of it. BUY cv 71, Buy_Rank #2, PullbackBuy_VWAP (L1-favoured family), Trending, buy-limit @209.73 at Entry_Distance_ATR -0.35 - non-extended, 1.1% below the close. Quality_Pass FALSE (Quality_Rank 19/31) blocks NEW entries and SAP is in this book. NOT a floor failure and NOT a valuation failure - MoS_FV -1.273 is the SHALLOWEST in the entire book, val_adj only -6. Purely the F-Score/FCF screen. Ledgered as a direction:none counterfactual per learnings advisory (d)(iii) so the gate's cost gets priced. Scorecard: PullbackBuy_VWAP|buy n=4 at 0.25/0.25, report-only, no bias applied. SAP fell -4.01% on a -2.18%-median tape. |
| SNOW | Snowflake Inc. | 319.80 | NO ACTION | 324.79 | 311.70 | 326.66 (+0.6%) | 344.24 (+6.0%) | 446.58 (+37.5%) | Snowflake was the top-ranked buy signal but it fails our financial-quality screen and, once adjusted for how richly it is priced, also falls a point short of our action threshold. It is also asking us to pay ABOVE today's price on a day the stock fell 3.5%, which is not a discount entry. Recorded, not acted on. OPERATIONAL: DOUBLE-BLOCKED. (1) Quality gate: Quality_Pass FALSE (Quality_Rank 20.5/31) blocks NEW entries; SNOW is. (2) Floor: MoS_FV -1.849 -> val_adj -9 leaves adj 64, ONE short of 65. BUY cv 73, Buy_Rank #1, PullbackBuy_VWAP, Trending. Note the printed entry 324.79 sits ABOVE the 319.80 close (Entry_Distance_ATR +0.38) - the model wants to pay up into a -3.51% session. Scorecard: PullbackBuy_VWAP|buy n=4 at 0.25/0.25, report-only. Ledgered as a direction:none counterfactual per learnings advisory (d)(iii). |
| MSFT | Microsoft Corp | 501.02 | NO ACTION | 495.37 | 484.97 | 496.85 (+0.3%) | 510.83 (+3.1%) | 656.19 (+32.5%) | Microsoft again shows a buy setup but again fails our financial-quality screen, and its score falls ten points short of our action threshold once adjusted for valuation. Fifth consecutive session blocked on both counts. Recorded, not acted on. OPERATIONAL: DOUBLE-BLOCKED. (1) Quality gate: Quality_Pass FALSE (Quality_Rank 17/31) blocks NEW entries; MSFT is in this book. (2) Floor: MoS_FV -1.747 -> val_adj -9 leaves adj 55, TEN short of 65. BUY cv 64, Buy_Rank #3, PullbackBuy_VWAP, Trending, buy-limit @495.37 at Entry_Distance_ATR -0.54. Scorecard: PullbackBuy_VWAP|buy n=4 at 0.25/0.25, report-only. Ledgered as a direction:none counterfactual per learnings advisory (d)(iii). |
Outcome & track record
Accuracy at the time of this record.
29 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.