Recommendations
2 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. | 107.69 | SELL ALL | 106.23 | 111.93⚠ | n/a | n/a | 66.96 (-37.0%) | Applied Optoelectronics has broken its stop decisively and just announced a million share sale that dilutes existing holders, so we are exiting the position in full. The business itself is doing well - record quarterly revenue up 86% - but the company is growth by issuing stock, which is an open-ended supply of new shares hanging over the price, and the stock has already fallen 26% in a week and 35% in a month. Our 12-week model now points 37% lower, and the shares have closed below their long-term trend line for the first time. This is a loss we are taking rather than a position we are defending. OPERATIONAL: 7th re-fire of the 08-25 MOO order (unexecuted; executor 9 sessions stale, last_run_date 2026-08-18) - escalated to market-on-open per UT-3, not re-limited. L2 basis: decisive close below stop (106.23 vs 111.93 = -5.09%; vs scan Stop_Price 128.50 = -17.3%) PLUS negative 12wk (66.96 = -36.97%, deteriorated from 77.51). First close below EMA200 (106.23 vs 106.64); EMA20 120.64 / EMA50 126.32 far overhead; Consolidation_Bearish, Trend 44 / Mom 33 / Vol 28; Exit_Strategy 'immediate'. UT-9 APPLIED: the row's PROFIT_ARMED print is INERT - Gain_ATR -3.93, unrealized -29.19%; the arm comes via T12_Progress_Pct 158.65 (progress toward a COLLAPSING downside target), the textbook arm-on-loss mislabel. Not read as a profit-take; the exit rests on stop-break + neg-12wk + dilution news. Valuation blind: Val_Signal NA, FV_per_share -3.38 (negative intrinsic), F-Score 4, Quality_Rank 28/31 -> val_adj 0, no amplify, no tier bump (CLAUDE.md ss9). SCORECARD: FailedBreakout_Down_20D|sell reached n=5 this run - the book's FIRST ACTIONABLE CELL in 15 weeks - hit_1w 0.50 / hit_4w 1.00 (5/5), computed bias +0 so no adjustment applied, but the cell says this engine's bearish calls in this family reach their downside targets. Realized - (-29.19%) vs cost 150.03; proceeds (3.74% of equity). Estimates: 1wk/4wk n/a - the row carries NO Target_Price (immediate-exit bearish signal emits none), nothing to interpolate, not invented; 12wk 66.96 (-36.97%) is the downside stepped out of; model band 88.75-135.36. Execution-gap on this line alone is now roughly -cumulative (-988.89 / -3173.73 / +208.62 / -164.16 / -2411.10). · news |
| PLTR | Palantir Technologies Inc. | 186.38 | BUY — QUEUED @165.83 | 165.83 | 158.46 | 166.88 (+0.6%) | 176.80 (+6.6%) | 265.46 (+60.1%) | Palantir is the strongest signal in the book - top-ranked, maximum conviction for a second day running, and one of only ten names that rose on a broadly red session. The business is compounding fast: revenue up 94% with US commercial bookings up 149% and a record billion of new US commercial contracts. The catch is the price - the shares are up 50% in a month and now sit essentially level with the average analyst target, so we are not paying up. We place a limit order 12% below the current price, at the level the model identifies as fair entry, and buy only if the market comes to us. OPERATIONAL: QUEUED, not bought - Entry_Distance_ATR -2.78 (close 186.29 vs entry 165.83 = 12.3% past the model entry); UT-6 governs (an extended name auto-queues, never chases). REPRICED 163.94 -> 165.83 per the Step 7 provenance rule - the 08-28 limit never came close to filling (session low ~182) and is NOT carried forward; the 08-22 @156.52 order was withdrawn 08-25. Entry is not invented: VWAP_Distance +12.34% means 165.83 IS the anchored VWAP, exactly where a PullbackBuy_VWAP is designed to fill, and it sits just under EMA20 168.98 so a fill tests trend support. Entry range 163.99-167.67 (+-0.25 x ATR 7.365). Stop 158.46 (-4.4%, ~1.0 ATR). Stability 4-of-5 buy-pool snapshots (64 > 64 > 61 > 100 > 100); Mostly_Aligned, Trending, Trend 90 / Mom 67 / Vol 33. SIZING: Portion 66.95% x equity x buy_pct 20% =; x0.50 size modulator (MoS_FV -13.08 <= -3) =; / 165.83 = 392.29 -> = = 6.69% of equity. max_position_pct 60% and both non-binding. Quality gate PASSED (Quality_Pass True, F 8, Quality_Rank 6/31). Estimates use the Step 7 fallback with f = 0.096 (27 graded >= 10, so L5's 0.30 does not bind; the CSV has only a single Est_Low/Est_High band, not the ADR-0013 per-horizon Est_*_Point columns): 1wk 166.88 (+0.64%), 4wk 176.80 (+6.62%), 12wk 265.46 (+60.08%) - WARNING exceeds DCF anchor 46.62, projection assumes growth beyond priced-in. CAUTION carried: PullbackBuy_VWAP|buy is n=4 at hit_1w 0.25 / hit_4w 0.25 - report-only, bias 0, but a real argument against expecting the 4wk target. Expires 2026-09-02 (anchor + 3 trading sessions); withdraw automatically if conviction falls below 65. · news |
| CRM | SalesForce Inc | 257.54 | BUY — QUEUED @257.66 | 257.66 | 211.73 | 266.48 (+3.4%) | 349.52 (+35.7%) | 364.80 (+41.6%) | Salesforce delivered the quarter that settles the argument about whether AI helps or hurts it: profits came in 80% above expectations, management raised full-year earnings guidance by 18.5%, and its AI products are now a billion recurring revenue line growing over 200% a year, alongside a new partnership embedding Anthropic's Claude across Slack and Salesforce. The shares jumped 23% and have kept climbing since. This is one of only two names in the book our valuation work still calls fairly priced rather than expensive, and the only one whose 12-week projection sits inside its own discounted-cash-flow anchor. We buy at half size, and only on a further move up. OPERATIONAL: QUEUED as the model's own Buy Stop @257.66 (Entry_Distance_ATR +0.11) - it fills ONLY on continued strength above Friday's range, self-limiting in the same way the anticipate-slot buy-stop is. REPRICED 213.78 -> 257.66 per the Step 7 provenance rule: the 08-28 GTC limit was placed for L6 gap discipline, CRM never traded within 15% of it, and the rule explicitly covers a previously-queued name that has run past its limit AND is overbought (RSI 80.79 > 75) - reprice to the live Entry_Price or demote to WATCH. Repriced, not republished stale. L6 WEIGHED AND ANSWERED: the 08-26 +22.58% gap is an earnings-power re-rating (adj EPS vs est = 80% beat; FY guide +18.5% to), not a sentiment pop of the UT-1/MU kind, and the stock has HELD and extended (+1.82%, then +1.57% on a -1.71%-median tape). Cautions priced in via size: RSI 80.79, VWAP_Distance +20.31% (genuinely extended), and UT-12 folds MomentumContinuation_Up|buy into L1's discount-on-ties list (own-book cell n=2 at 0/2 on 1wk, median err -4.19%). SIZING: Portion 66.95% x equity x buy_pct 20% =; x0.50 =; / 257.66 = 252.48 -> = = 6.68% of equity. THE MODULATOR IS 0.50, NOT THE FILE'S 0.75, AND THIS IS STATED NOT SILENT: fairvalue_T0 prices CRM at 209.06 vs a 256.00 anchor close (+22.5% stale), and MoS_FV recomputed live (256.00 / FV_per_share 59.55 = P_FV 4.30 -> MoS -3.30) crosses the <= -3 tier. Quality gate PASSED (Quality_Pass True, F 7, Quality_Rank 15/31). Stop 211.73 is WIDE - -17.8% / ~3.0 ATR, chandelier_trail on a post-gap name, sitting just above the pre-gap base; correct invalidation level but of risk on - flagged deliberately. Entry range 253.83-261.49 (+-0.25 x ATR 15.310). Estimates (f = 0.096): 1wk 266.48 (+3.42%), 4wk 349.52 (+35.66%), 12wk 364.80 (+41.58%) - NO DCF annotation, DCF_per_share 379.39 is ABOVE the 12wk target, unique among this book's buy candidates. Expires 2026-09-02; withdraw automatically if conviction falls below 65. · news |
| DELL | Dell Technologies Inc | 456.01 | HOLD | 456.24 | 427.70 | 460.51 (+0.9%) | 500.74 (+9.8%) | 579.63 (+27.0%) | We hold Dell in full into its quarterly results on 3 September and deliberately leave the stop where it is rather than tightening it. The shares fell 3.4% on Friday and the position slipped back to a small loss, but nothing in the signal has broken: the stock is still above all its trend lines, the 12-week projection is 27% higher, and analysts expect earnings to more than double year-on-year. Moving the stop up to the model's level would place it within a single day's normal price swing three days before a binary event - that is not risk control, it is a near-guaranteed shake-out before the news. OPERATIONAL: NO TRIM BASIS ON ANY ORIGINATION CLASS - no SELL print (HOLD, FailedBreakdown_Up_20D, cv 54); Exit_Warning BLANK; NO PROFIT_ARMED (Gain_ATR -0.23, T12_Progress_Pct 78.71, below the 90 arm threshold); close 456.24 above stop; above EMA20 451.14 / EMA50 423.03 / EMA200 290.83; Target_12Week 579.63 = +27.05%. ADR-0020: stop 427.70 vs peak_stop 455.32 = 6.07% erosion, INSIDE the 15% band - no mandatory trim. STATED DEVIATION FROM THE MODEL STOP: the scan prints Stop_Price 445.12 and adopting it would also improve ADR-0020 erosion to 2.24%, but 445.12 sits 0.50 x ATR below the close (ATR 22.25 = 4.88% of price) - noise width, not a risk line - and DELL reports FQ2 in 3 sessions (2026-09-03), squarely inside the <=5-day catalyst window where CLAUDE.md directs HOLD/trail THROUGH the event and trim only on a confirmed lower-high or decisive stop break. 427.70 (1.28 ATR, -6.26% from close, -7.28% from cost 461.298) is retained as the real invalidation line; re-tighten to the model level after the print. Consequence accepted and stated: up to more downside carried through the event than the model line implies. Conviction fell and the position is back underwater at -1.10%. News NEUTRAL/constructive but two-sided: consensus EPS (+113.4% YoY) on revenue 25bn (+52% YoY), ISG 06bn (+67%), Zacks Rank #1 with Earnings ESP +3.35%, forward P/E 25.7 / PEG 0.98 - against at least one sell-side downgrade published into the print. 1wk estimate uses f = 0.096 off the 456.24 hold reference. · news |
| MSFT | Microsoft Corp | 507.29 | NO ACTION | 516.05 | 482.58 | 522.47 (+1.2%) | 582.98 (+13.0%) | 680.11 (+31.8%) | Microsoft was the third-ranked buy signal and one of the few names to rise on a red day, but it fails our quality screen and its score falls short of the bar once we adjust for how richly it is priced. Recorded, not acted on. OPERATIONAL: DOUBLE-BLOCKED. (1) Quality gate: Quality_Pass FALSE (F-Score 6, Quality_Rank 17/31) blocks NEW entries and MSFT is in this book. (2) Floor: MoS_FV -1.67 -> val_adj -8 leaves adj 57, EIGHT short of the 65 floor. Signal was BUY cv 65, Buy_Rank #3, MomentumContinuation_Up, Trending, Trend 90, buy-stop @516.05 at Entry_Distance_ATR +0.23, close +1.68% on a -1.71%-median tape; RSI 73.07 extended. UT-12 additionally discounts the MomentumContinuation_Up|buy family (own-book n=2 at 0/2 on 1wk). Ledgered as a direction:none counterfactual per learnings advisory (d)(iii) so the quality gate's cost is priced before the gate is ever re-evaluated. |
| AAPL | Apple | 316.85 | BUY-STOP | 320.93 | 301.43 | 324.68 (+1.2%) | 359.94 (+12.2%) | 319.55 (-0.4%) | Apple flashed an early-warning buy setup at high conviction, but it is the first such print in a row of no-signal days, and our rule requires the setup to persist for at least two of the last three days before we act on it. One day is a flicker, not a pattern. Recorded and watched - if it prints again on Monday it becomes actionable Tuesday. OPERATIONAL: ANTICIPATE slot INELIGIBLE - requires BUY - ANTICIPATE in >=2 of the last 3 snapshots; AAPL's last three are WATCH 58 > NO TRADE 0 > BUY-ANTICIPATE 83 =, a cold flip. Conviction 83, adj 73 after val_adj -10, comfortably above the 55 anticipate floor, and Quality_Pass True (F 9, Quality_Rank 3/31) - eligibility, not quality or conviction, is the sole blocker. Buy-stop would have been @320.93 (Entry_Distance_ATR +0.19), Trend 90, Consolidation_Bullish, 0.5x normal new-BUY. Counterfactual aggregate independently supports standing down: anticipate n=8, median 1wk -0.73% / 4wk -8.81% ['saved']. Ledgered as a direction:none counterfactual so the cost of not queueing is priced. Note Target_12Week 319.55 is BELOW the 319.70 close - a flat-to-dead 12-week view regardless. |
Outcome & track record
Accuracy at the time of this record.
27 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.