Recommendations
2 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 |
|---|---|---|---|---|---|---|---|---|---|
| PLTR | Palantir Technologies Inc. | 182.53 | BUY — QUEUED @175.81 | 175.81 | 165.94 | 180.22 (+2.5%) | 190.50 (+8.4%) | 260.11 (+47.9%) | Palantir's AI platform keeps winning enterprise distribution - it rose 7.9% on an expanded PwC US partnership that opens another channel into large corporate, on top of a business compounding at a 155% Rule-of-40 with 157% net dollar retention. The technical setup is a pullback-to-VWAP buy at strong conviction rather than a chase, so we queue a limit below the market and let the stock come to us; the offset is that the shares are expensively priced against any intrinsic anchor, which is why we size at half. Operational: adjusted conviction 86 -10 (val_adj, MoS_FV -13.405 clamped at floor) -5 (scorecard_bias, PullbackBuy_VWAP|buy n=5 at 0.25/0.25, newly ACTIONABLE) = 71, clears the 65 floor by 6. Quality_Pass True, Quality_Rank 6/31 - gate clears. Entry_Distance_ATR -0.68 (extended past the limit) so QUEUED not bought; action price is the anchor snapshot's own Entry_Price, no carried-forward level. Size 0.6695 x 1,016,240.86 equity x 20% buy_pct =, x0.5 size modulator (MoS_FV <= -3) = / 175.81 =. Risk if stopped 387 x 9.87 = = 0.38% of equity. Estimates use f=0.30 per L5 (calib_1w -0.141, degenerate). 12wk 260.11 exceeds DCF anchor 46.62 - projection assumes growth beyond priced-in. expires_on 2026-09-09 = 3 trading sessions from the 09-04 anchor (09-07 Labor Day). Re-arm trigger if expired: a fresh PullbackBuy_VWAP print with adjusted conviction >= 65. Countervailing view noted: Michael Burry publicly short-biased, overvaluation critique is exactly what val_adj -10 encodes. · news |
| MU | Micron Technology, Inc. | 958.16 | BUY | 958.16 | 918.88 | 983.17 (+2.6%) | 1041.53 (+8.7%) | 1024.59 (+6.9%) | Micron is the highest-quality name in this book's universe (Quality_Rank) buying into a memory cycle that is sold out rather than speculative - HBM3E and HBM4 are fully booked through 2027 with demand extending into 2028, supply constraints are holding contract pricing elevated, and consensus sits at Strong Buy with a mean target near The stock just reclaimed and the signal is a failed breakdown that resolved upward, giving a market entry at zero extension rather than a chase. The honest caveat is macro, not company: the market now prices better than a 60% chance of a Fed hike on 16 September, and the sell-side read is that the FOMC decision could move this stock harder than its own FQ4 print on 30 September. Operational: adjusted conviction 76 -6 (val_adj, MoS_FV -1.160 GROWTH_PRICED_IN) + 0 (scorecard_bias) = 70, clears the 65 floor by 5. FailedBreakdown_Up_20D|buy is n=3 at 0.333/0.50 - BELOW the actionable floor, so printed as a warning and NOT subtracted; L1/UT-12 discount this family on ties and this is not a tie. Entry_Distance_ATR 0.00, Buy_Rank #5. Size 0.5071 x 1,016,240.86 equity x 20% buy_pct =, x0.75 size modulator (-3 < MoS_FV <= -1) = / 958.16 = =. Risk if stopped 80 x 39.28 = = 0.31% of equity. WARNING executes at the 09-04 open, one hour after August payrolls at 08:30 ET - reprice if the open gaps >~1.5% (L8). Estimates use f=0.30 per L5. 12wk 1024.59 exceeds DCF anchor 772.94 AND prints BELOW the 4wk 1041.53 (backlog vii inversion) - read the 4wk as the trade objective and the 12wk as a caution flag. Stale overlay MU override (WEEK 2026-07-05, 61 days) carries no numeric delta and is NOT applied. · news |
| AAOI | Applied Optoelectronics, Inc. | 100.38 | SELL ALL | 100.38 | 111.93⚠ | n/a | n/a | 57.22 (-43.0%) | We are cutting this position in full. The company announced a million at-the-market equity offering on top of the million already raised - open-ended dilution that the market read immediately, sending the shares down 12% even against a record quarter. The chart agrees: the stock has closed below its risk line for four straight sessions and below its 200-day average for four, with every shorter moving average stacked bearishly above it, and our own twelve-week model now projects 43% lower from here. A record quarter funded by issuing stock into a falling price is not a thesis we want to hold through. Operational: STRONG SELL - REDUCE cv76 (rising -> 76), Sell_Rank #1, engine 90.04 with rationale 'target full exit'. Close 100.38 vs recorded stop 111.93 = -10.32% (deepest yet, 4th session); 4th consecutive close below EMA200 (106.26) with EMA10 109.70 / EMA20 114.95 / EMA50 122.95 stacked above; Target_12Week 57.22 = -43.0%; VWAP_Distance -22.26%. Both L2 legs armed 4 sessions. Realized - (-33.09%) vs 150.03 cost; proceeds. This is a LOSS-CUT not a profit-take - the PROFIT_ARMED print is the arm-on-loss mislabel and is INERT under UT-9 (Gain_ATR -6.43). TENTH re-fire under L2+L3+UT-3/UT-11. CRITICAL: execution verb corrected to 'market' - the ten prior AAOI exit cards were written 'market_on_open', which paper_executor.py _EXEC_KINDS (line 112) / _eligibility (line 554) rejects BEFORE the skip-log path, making them invisible; ledger tally is a perfect separation, ('sell','market') 5 cards -> 5 fills, ('sell','market_on_open') 22 cards -> 0 fills ever. Estimates: 1wk/4wk n/a - the REDUCE row prints a blank Target_Price, no number synthesized. SCORECARD CAUTION stated not buried: RallySell_BearTrend|sell is n=4 at 0.00/0.00 on this book's own data - every prior exit in this family looked early at both horizons; report-only so nothing is adjusted, and the exit is taken anyway because a -10.32% broken stop with a -43% forward view and open-ended dilution is exactly the case L2 exists for. Valuation originates nothing (Val_Signal NA, FV_per_share -3.38). · news |
| NVDA | NVIDIA Corporation | 228.45 | SELL 30% | 228.45 | 215.33 | 243.64 (+6.6%) | 279.08 (+22.2%) | 250.12 (+9.5%) | We are taking a third of this position off the table on target exhaustion, and holding the rest. The stock has run to within 9% of our own twelve-week projection while momentum has started to diverge from price - the classic signature of a move that has done most of its work - so we bank a slice and raise the risk line under the remainder. This is a risk trim, not a change of view: Nvidia just announced a roughly billion acquisition of Hugging Face, brokers sit at 46 Strong Buys out of 51, and every forward horizon we model is still positive. That is precisely why the trim is 30% and not more. Operational: ADR-0012 profit-take, ARMED + one tick FIRED. Armed = PROFIT_ARMED printed with T12_Progress_Pct 91.34 (>=90); Gain_ATR +0.21 is POSITIVE so UT-9 does NOT make the arm inert (contrast AAOI at -6.43 where it does). Fired = tick (a), a second Exit_Warning code RSI_DIV on the same row. Ticks (b)/(c)/(d) all checked, none fires: conviction ROSE; Target_12Week 250.12 > 1.02 x close (233.02); row is HOLD not NO TRADE. G1 softening does NOT reach it - it protects fresh BreakoutUp_*/MomentumContinuation_* at conviction >=80 and this signal is AnticipationUp_VCP, outside those families - so the trim is MANDATORY, not optional. One tick -> profit_take_1 = 30%. Valuation amplify does NOT apply (MoS_FV -2.400 is not <= -3), portion stays 30%. 168 x 0.30 =, proceeds, realized + (+0.73%). Residual, stop RAISED 213.25 -> 215.33. Estimates rendered as upside forgone (f=0.30 per L5); 12wk exceeds DCF anchor 163.98. TENSION RECORDED: this banks on a position 0.21 ATR above cost, armed entirely by the T12 exhaustion branch not by gain magnitude; the identical card was issued 08-28 (SELL 50 @227.98) and withdrawn 08-29 when Gain_ATR flipped negative. The pending 08-29 PROPOSED block (X2) proposes Gain_ATR >= 1.0 to arm, which would suppress this card - PROPOSED is inert by design and is NOT applied. Watch NBIS warrant lock-up 09-11 (~21M shares). · news |
| DELL | Dell Technologies Inc | 516.39 | HOLD | 515.51 | 438.60 | n/a | 711.00 (+37.9%) | 685.53 (+33.0%) | Holding the whole position and raising the stop. Dell's quarter reset the story - record billion of AI-server orders, a billion backlog and full-year revenue guidance lifted to about billion - and the shares have followed through to a fresh 52-week high rather than fading the print, which is the behaviour of a re-rating rather than a spike. We are not trimming a winner into strength, and we are not adding at these levels either; instead we lift the risk line beneath the position and let it run. Operational: STRONG BUY - ADD cv100, Buy_Rank #1, adjusted 90 after val_adj -10 - the highest adjusted conviction this book has recorded - and the ADD is DECLINED (see the separate blocked_learnings card). Stop RAISED 432.27 -> 438.60 (scan's live line, 2.02 ATR below close 516.39, +19.46% headroom). NO TRIM: not armed (Gain_ATR 1.43 < 3.0, T12_Progress 75.33 < 90), and G1 protects the RSI_DIV print outright - a fresh BreakoutUp_52W at conviction 100 with a +32.7% 12wk view is exactly the trending breakout G1 exists to keep whole. Position, + (+11.94%) vs 461.298 cost, 36.23% of equity. Countervailing view stated: UBS argues the near-doubling YTD leaves little further upside (https://finance.yahoo.com/markets/stocks/articles/dell-stock-nearly-doubled-2026-191031235.html). Scorecard: BreakoutUp_52W|buy is n=2 at 0.00/0.00 on this book's own data - report-only, but it does not argue for an add either. · news |
| AAPL | Apple | 328.21 | HOLD | 329.13 | 314.62 | n/a | 372.66 (+13.2%) | 344.99 (+4.8%) | Holding through the product event and raising the stop. Apple's 'Surprise and Shine' launch - iPhone 18 Pro and the foldable - is three trading sessions away, and cutting a position into its own catalyst is how you end up on the wrong side of the reaction in both directions. The position has drifted to within 5% of our twelve-week projection while conviction has risen, so the right response is a tighter risk line beneath it, not a sale. Operational: ADR-0012 ARMED but NOT FIRED - PROFIT_ARMED with T12_Progress 95.14, Gain_ATR +0.17 (positive, so UT-9 does not void the arm), and ZERO ticks fire: no second Exit_Warning code on the row; conviction ROSE; Target_12Week 344.99 > 1.02 x close (334.77); not NO TRADE. ADR-0012 prescribes a MANDATORY trail-raise in this state: stop 305.86 -> 314.62 (scan's chandelier line, 1.87 ATR below close 328.21, +7.31% headroom). Catalyst-aware hold per the skill's catalyst rule - event 09-09 is inside the <=5 trading day window - so no pre-trim and no add; trim only on a confirmed lower high or a decisive break of 314.62. Position @326.97, + (+0.38%) on day two. The anticipate counterfactual cell (n=9, median 4wk -8.81%) is grading this entry live - do NOT average down. |
| CRM | SalesForce Inc | 264.43 | HOLD | — | 251.77 | n/a | n/a | 376.81 | Holding, with the risk line unchanged and a specific trigger to watch. Salesforce has rallied roughly 40% in a month on a guidance raise and the Claudeforce partnership with Anthropic, and its AI business is compounding fast - Agentforce and Data Cloud annual recurring revenue near billion, up more than 210% year on year. The stock is now stretched well above its own average price and the internal momentum reading has faded even as the price makes new highs, so this is a name to watch rather than add to; the next scheduled catalyst is the Dreamforce investor day on 16 September. Operational: SECOND consecutive NO TRADE print, and it does NOT fire a trim - correcting yesterday's entry, which stated a second print would make this a mandatory trim candidate. ADR-0012 tick (d) is a FIRE tick and requires an ARMED position; CRM is NOT armed (Gain_ATR 0.56 < 3.0, T12_Progress 70.18 < 90, no Exit_Warning code at all), so ADR-0012 offers no trim path. G3 independently refuses one: it requires a flat/negative forward view or a bearish signal, and Target_12Week 376.81 = +42.5% with the close making a new high (+2.92% to 264.43). Condition named honestly: Momentum_Score COLLAPSED to 20 against Trend 90 (Conflicted), RSI 81.88, VWAP_Distance +17.05% - a post-earnings melt-up extended past its average target. RE-ARM TRIGGER: a confirmed lower high OR a decisive break of 251.77 - not a third NO TRADE print on its own. Stop held at 251.77: the scan prints no Stop_Price under NO TRADE and a 2.0xATR chandelier (240.17) sits BELOW the recorded line, so the ratchet holds. Position @257.66, + (+2.63%). Dreamforce Investor Day 09-16 is ABSENT from the parent horizon file - systemic finding 4. · news |
| DELL | Dell Technologies Inc | 516.39 | HOLD | 515.51 | 438.60 | n/a | 711.00 (+37.9%) | 685.53 (+33.0%) | Counterfactual record: the model wanted to add aggressively to Dell here and we declined. The signal was as strong as this book has ever produced - a fresh 52-week breakout at maximum conviction, top-ranked in the buy list - but the entry sits 21% above where the stock traded before its earnings, two sessions into the re-rating, with daily volatility having spiked to more than 7% of the share price. Buying a quarter of a million dollars of a name that already accounts for a third of the book, at that entry, an hour after a payrolls print, is a worse trade than the signal makes it look. We hold what we own and let the stop do the work. Operational: STRONG BUY - ADD cv100, Buy_Rank #1, 112.34, Buy Stop @515.51, Entry_Distance_ATR -0.02; adjusted conviction 90 after val_adj -10 - would have been slot #1 and would have sized to / (capped by max_position_pct 60%, not by conviction). DECLINED on two ACTIVE learnings that bind harder today than yesterday when the same call was made at 492.20: L6 (no post-earnings gap-chase) - entry 515.51 is +21.3% above the pre-earnings 425.00 close; and UT-10 (no pyramiding at spiking ATR) - ATR_Price 38.46 = 7.45% of price, up from 34.95 yesterday and ~25 pre-print, and UT-10 gates ADD queues on a NON-SPIKING ATR. This is explicitly NOT a concentration objection (CLAUDE.md section 9 forbids that reasoning); the objection is entry quality and volatility. Ledgered direction:none so the cost of the refusal is priced by the counterfactual grader. Scorecard: BreakoutUp_52W|buy n=2 at 0.00/0.00, report-only. · news |
| SNOW | Snowflake Inc. | 356.47 | WATCH | 342.98 | 276.15 | n/a | 476.63 (+39.0%) | 497.04 (+44.9%) | Counterfactual record: highest raw conviction in the buy pool and blocked before it could be sized. Snowflake's balance-sheet quality screen fails, and we do not open new positions in companies that fail it however good the chart looks. Operational: STRONG BUY cv100, BreakoutUp_20D, Buy_Rank #2, adjusted 91 (val_adj -9, MoS_FV -1.849) - clears the 65 floor by 26 and is BLOCKED by the hard quality gate (Quality_Pass False, Quality_Rank 20.5/31, F-Score/FCF screen failed). Would also have failed L6 independently: close 356.47 is a +16.55% single-session earnings gap, and Entry_Distance_ATR -0.51 puts it past the buy-stop. Ledgered per advisory (d)(iii) so the gate's cumulative cost is measurable before it is ever re-tuned. |
| MSFT | Microsoft Corp | 510.12 | WATCH | 496.38 | 484.80 | n/a | 513.60 (+3.5%) | 660.46 (+33.1%) | Counterfactual record: clears the conviction bar on arithmetic and is blocked by the quality screen. Operational: STRONG BUY cv86, PullbackBuy_VWAP, Buy_Rank #3, adjusted 72 (val_adj -9 MoS_FV -1.747; scorecard_bias -5, PullbackBuy_VWAP|buy n=5 at 0.25/0.25 now ACTIONABLE) - clears the 65 floor by 7, BLOCKED by Quality_Pass False (Quality_Rank 17/31). Entry_Distance_ATR -1.19 would have made it a QUEUED gtc_limit at 496.38 rather than a market buy. Ledgered per advisory (d)(iii). |
| SAP | SAP AE | 217.03 | WATCH | 217.03 | 213.85 | n/a | 229.76 (+5.9%) | 290.61 (+33.9%) | Counterfactual record: clears the conviction bar on arithmetic and is blocked by the quality screen. Operational: BUY cv76, FailedBreakdown_Up_20D, Buy_Rank #6, adjusted 70 (val_adj -6, MoS_FV -1.273) - clears the 65 floor by 5, BLOCKED by Quality_Pass False (Quality_Rank 19/31). Entry_Distance_ATR 0.00 (non-extended market entry) - the gate is the only thing stopping it. Ledgered per advisory (d)(iii). |
| TSLA | Tesla Inc | 376.36 | WATCH | 369.56 | 328.23 | n/a | 452.21 (+22.4%) | 349.92 (-5.3%) | Counterfactual record: misses on both arms. Operational: BUY cv74, BreakoutUp_20D, Buy_Rank #7, adjusted 64 (val_adj -10, MoS_FV -18.723 clamped) - ONE point short of the 65 floor, and independently BLOCKED by Quality_Pass False (Quality_Rank 31/31, last in the universe). Target_12Week 349.92 also prints BELOW the 4wk 452.21 and only -7.0% above the 376.36 close - the backlog (vii) inversion pattern. Ledgered per advisory (d)(iii). |
Outcome & track record
Accuracy at the time of this record.
33 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 →
-0.141 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.