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. | 103.13 | SELL ALL | 103.13 | 86.90 | n/a | n/a | 58.78 (-43.0%) | Exit the position outright. Applied Optoelectronics has broken decisively below its risk line for a third straight session (103.13 vs a 111.93 stop, -7.86%) and closed under its 200-day average for the third time, with the engine's 12-week view now pointing 43% lower; the signal has strengthened into a STRONG SELL at the book's top sell rank rather than fading. The company is an aggressive capacity build by issuing stock continuously - a fresh at-the-market offering on top of already raised - which is open-ended dilution into a falling optics tape, and intrinsic value screens negative, so there is no valuation floor to wait for. Record 86% revenue growth is real but is not what the price is trading on. OPS: 9th consecutive re-fire; 2nd session the executor dropped the sell leg - escalated to market-on-open per UT-3/UT-11. L2 (stop-break + negative 12wk) is the origination basis; valuation originates nothing here (Val_Signal NA, FV_per_share -3.38). PROFIT_ARMED print is INERT per UT-9 (Gain_ATR -5.78). Scorecard caution logged not applied: RallySell_BearTrend|sell is n=3 at 0.00/0.00 own-book - expect this exit to look early. No Target_Price on the row, so 1wk/4wk are n/a rather than fabricated. Realizes -31.26% vs 150.03 cost. · news |
| DELL | Dell Technologies Inc | 492.20 | HOLD | 492.20 | 432.27 | 498.91 (+1.4%) | 562.10 (+14.2%) | 617.55 (+25.5%) | Hold the full position and raise the protective stop. Dell's fiscal Q2 was the strongest AI print of the quarter - adjusted earnings of against expected, a record 9bn of AI-server orders, a $95bn backlog and full-year revenue guidance lifted roughly $25bn to about $192bn - and the shares closed +15.75% in response. Conviction jumped from, the 12-week view sits 25% above the close, and the position is now +6.70%. This is a winner in a confirmed uptrend: the discipline is to trail the stop up behind it, not to take profit into strength, and equally not to chase the gap with fresh money. OPS: stop RAISED 412.30 -> 432.27 (scan's live line, 1.71 ATR below close, just above EMA50 427.01). NOT PROFIT_ARMED (Gain_ATR 0.88 < 3.0; T12_Progress 79.7% < 90) so no profit-take tick exists. G3 decisively unsatisfied - bullish signal + strongly positive 12wk = do not trim. No ADD per L6 (no post-earnings gap-chase) and UT-10 (no pyramiding at spiking ATR 34.95). Yesterday's stop-breach cancellation is now measured at +in one session. Horizon file still has ZERO DELL coverage - systemic finding 4. · news |
| NVDA | NVIDIA Corporation | 224.41 | HOLD | 224.41 | 213.25 | 226.03 (+0.7%) | 241.34 (+7.5%) | 240.52 (+7.2%) | Hold. Nvidia rallied 3.21% to 224.41 and conviction improved from, so the trend case is firming rather than fading; the position is only 1.05% underwater and the 12-week view remains alive at 240.52. There is no deterioration to act on, so the position stays whole with its existing risk line intact. OPS: PROFIT_ARMED fires again on T12_Progress 93.3% and is INERT per UT-9 (Gain_ATR -0.28, position underwater = arm-on-loss mislabel). All four ADR-0012 fire ticks checked, none fires: (a) no other Exit_Warning; (b) conviction ROSE +15; (c) T12 240.52 = 1.072x close, alive; (d) zero NO TRADE prints. Stop deliberately NOT loosened to the scan's 207.48 - ratchet moves up only; 213.25 now sits 1.32 ATR below close (was 0.53 ATR). Watch: NBIS warrant lock-up 09-11 releases ~21M shares, an NVDA-adjacent supply event. |
| AAPL | Apple | 324.96 | HOLD | 324.96 | 305.86 | 329.51 (+1.4%) | 372.40 (+14.6%) | 336.63 (+3.6%) | Hold the newly-filled position through the product event. The anticipation buy-stop triggered on 09-02 and filled at 326.97; the stock closed 324.96, so the position is 0.62% under water on day one. Apple has the strongest trend reading in the book and the 'Surprise and Shine' iPhone 18 Pro and foldable launch is four trading sessions away, with IDC projecting over 10 million first-year foldable shipments - the standing policy is to hold and trail through a catalyst that close rather than pre-trim into it. The caution is that the shares already trade above the sell-side's raised anchor, so the event has to deliver. OPS: anticipate slot CONSUMED - the row still prints BUY - ANTICIPATE cv77 with a fresh Buy Stop @328.04, but that is a stale Held=N artifact (scan 06:00:17 ran before the executor fill 06:00:35, UT-7) and re-queueing it would be an L6-adjacent chase 0.42 ATR above the close. NO ADD. Stop SET 305.86 (chandelier line), risk = 0.23% of equity. Catalyst-aware hold: 09-09 event inside the <=5-session window. The anticipate counterfactual cell (n=9, 4wk -8.81%) argued against this entry and is now grading it live - do not average down. · news |
| CRM | SalesForce Inc | 256.93 | HOLD | 256.93 | 251.77 | n/a | n/a | 366.13 (+42.5%) | Hold, but this is the position to watch. Salesforce's post-earnings melt-up - Q2 adjusted EPS of against expected, Agentforce and Data 360 recurring revenue near 9bn and up 210% year on year - has carried the shares 22% in a week and straight into the average analyst target, and the momentum behind the move has now stalled with the stock overbought at an RSI of 80 and trading 15.6% above its volume-weighted average. The engine has gone to NO TRADE on conflicting internals. Nothing yet justifies selling a position that is only 0.28% offside with an intact risk line, but the burden of proof has shifted. OPS: Momentum_Score COLLAPSED to 13 against Trend 76 = Conflicted consensus; NoTrade_Reason verbatim 'Consensus conflict + low conviction'. This is 1 of the 2 consecutive NO TRADE prints ADR-0012(d) requires - a second print next EOD makes it a mandatory trim candidate; CHECK THIS FIRST next run. Not PROFIT_ARMED (Gain_ATR -0.06, T12_Progress 70.17%). No stop break. Stop UNCHANGED 251.77 - a -0.28% session does not justify a raise. 1wk/4wk n/a: NoTrade rows print no Target_Price. Next catalyst Dreamforce Investor Day 09-16. · news |
| MU | Micron Technology, Inc. | 956.08 | NO ACTION | 956.08 | 927.16 | 964.12 (+0.8%) | 1039.85 (+8.8%) | 1016.17 (+6.3%) | Stood down, narrowly. Micron is the highest-quality name in this book's universe and prints a clean, non-extended buy at 956.08 with the shares having crossed intraday this week; the street consensus sits around and Philippe Laffont's fund raised its stake nearly 1,800%. What holds the book back is price, not quality - the shares screen as growth-already-priced-in, which costs six points, leaving the case two points short of the threshold required to commit capital. Worth watching for a better entry or a stronger print. OPS: adj 63 vs the 65 floor. Buy_Rank #3, Quality_Pass TRUE at Quality_Rank #1/31 - the gate is NOT the blocker here, val_adj -6 is. Entry_Distance_ATR 0.00 (perfectly non-extended). L1/UT-12 discount this FailedBreakdown family on ties (own-book cell n=3 at 0.50/0.50, report-only, no bias applied). The 60-day-stale overlay carries an MU override with no numeric delta - NOT applied. FQ4 lands 09-30, outside the horizon window. Ledgered as a direction:none counterfactual per advisory (d)(iii) so the 2-point miss gets priced. · news |
| PLTR | Palantir Technologies Inc. | 169.46 | NO ACTION | 174.40 | 166.16 | 175.58 (+0.7%) | 186.66 (+7.0%) | 241.48 (+38.5%) | Stood down on valuation. Palantir's signal is recovering - conviction back up to 71 on the pullback pattern this book generally prefers, and it is the second-ranked buy candidate - and it passes the quality screen cleanly. But the shares trade at more than fourteen times any defensible estimate of intrinsic value, the second-widest gap in the book, which takes the maximum ten-point penalty and leaves the case four points short. The model also wants to pay nearly 3% above the closing price, which is a chase by construction. OPS: adj 61 vs the 65 floor. Buy_Rank #2, Quality_Pass TRUE (rank 6/31) - gate clears; MoS -13.405 pins val_adj at the -10 clamp and IS the entire gap. Entry_Distance_ATR +0.60 = entry 174.40 is 2.9% ABOVE the 169.46 close. PullbackBuy_VWAP|buy own-book cell n=4 at 0.25/0.25 - report-only caution, no bias applied. Prior GTC @165.83 expired 09-02 unfilled and was NOT repriced. Ledgered as a direction:none counterfactual. |
| LITE | Lumentum Holdings | 870.58 | NO ACTION | 870.58 | 839.46 | 882.53 (+1.4%) | 995.05 (+14.3%) | 983.19 (+12.9%) | Blocked, twice over. Lumentum is the book's top-ranked buy candidate today on a fresh signal flip with the strongest momentum reading in the pool, but it fails the balance-sheet and cash-flow quality screen that governs new positions, and it is simultaneously the most expensive name in the entire universe - trading at roughly thirty-five times any defensible intrinsic value. Even setting the quality screen aside it would still fall four points short. The book's best-looking chart and its worst-looking valuation are the same name. OPS: adj 61 vs the 65 floor AND Quality_Pass FALSE (Quality_Rank 22.5/31) - double-stopped. Buy_Rank #1, Momentum_Score 60 (pool high), Entry_Distance_ATR 0.00. MoS -34.07 (FV vs price) is the deepest in the book, val_adj clamped at -10. L1/UT-12 discount the FailedBreakdown family. Also note the sector context that drives today's AAOI exit: optics sold off hard (-5.01% on LITE itself). Ledgered as a counterfactual so the quality gate's cost accumulates toward a measurable cell (systemic finding 5). |
| SAP | SAP AE | 209.69 | NO ACTION | 210.69 | 204.48 | 211.58 (+0.4%) | 219.92 (+4.4%) | 283.27 (+34.4%) | Stood down and fading. SAP was the closest call of the previous session, sitting exactly on the entry threshold with only the quality screen in front of it; a day later conviction has slipped from and the case is seven points short, so the screen is no longer even the binding constraint. No action. OPS: adj 58 vs the 65 floor AND Quality_Pass FALSE (Quality_Rank 19/31). MoS -1.273 is the shallowest in the book, val_adj only -6 - valuation is not the problem here, decaying conviction is. Entry_Distance_ATR +0.16. PullbackBuy_VWAP own-book cell n=4 at 0.25/0.25, report-only. Ledgered as a counterfactual (advisory d-iii). |
| MSFT | Microsoft Corp | 496.82 | NO ACTION | 495.78 | 486.01 | 497.17 (+0.3%) | 510.30 (+2.9%) | 641.62 (+29.4%) | Stood down for a fifth straight session. Microsoft keeps printing a modest buy on the pullback pattern but never gets close to the conviction required, and it continues to fail the quality screen that governs new positions in this book. Ten points short is not a near-miss. OPS: adj 55 vs the 65 floor AND Quality_Pass FALSE (Quality_Rank 17/31) - double-blocked five sessions running. val_adj -9 on MoS -1.747. Entry_Distance_ATR -0.11 (non-extended, the one thing in its favour). Ledgered as a direction:none counterfactual per advisory (d)(iii). |
| AAPL | Apple | 324.96 | BUY-STOP | 328.04 | 305.86 | n/a | 372.40 (+13.5%) | 336.63 (+2.6%) | No new anticipation order. The one anticipation slot this book carries was used on 09-02 and filled, so although Apple still prints an anticipation setup there is nothing left to queue - the position already exists and is managed as a hold into the 09-09 product event. OPS: the row's fresh Buy Stop @328.04 and Held=N flag are a scan/executor race artifact (scan 06:00:17 vs fill 06:00:35, UT-7) - NOT a flat position. Re-queueing would be acting on stale held-state AND an L6-adjacent chase 0.42 ATR above the close. Logged as a counterfactual so the not-adding decision is priced against the live AAPL hold card. · news |
Outcome & track record
Accuracy at the time of this record.
30 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.