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 |
|---|---|---|---|---|---|---|---|---|---|
| XLF | Financial Select Sector SPDR | 58.31 | BUY — QUEUED @57.72 | 57.72 | 56.97 | 58.46 (+1.3%) | 59.27 (+2.7%) | 58.46 (+1.3%) | Financials are the sector the market is rotating INTO as it rotates out of chips and AI hyperscalers, and this is the highest-conviction print the fund has given this book all month - conviction 88, rank 1 on the board, on the one buy family the book's own record actually favours. The order is a genuine pullback limit at, a full 1.01% BELOW the close and sitting right on the fund's VWAP between its 10- and 20-day averages, so the book is not paying up for a fund that closed within 0.17% of its 52-week high. The EMA ladder is stacked at every horizon from 5 days to 200, the bank complex is at record highs on strong earnings and fading private-credit worry, and the 10-year fell 6bp to 4.63% on the session. Crucially, XLF is the least Nvidia-exposed name in today's buy pool by a wide margin: on 08-24 it rose 1.29% while the chip funds fell 2.4-2.7%, so it is the one candidate that a disappointing Nvidia print could help on a relative basis rather than simply hurt. OPERATIONAL: GTC buy limit at, live from the 2026-08-26 open, expires 2026-08-28 (anchor + 3 sessions). Entry range - (entry +/- 0.25 ATR). Sizing 85.49% x x 20% buy_pct_of_portfolio =, size_mod 1.0x (valuation blind, all-ETF book), at =. Stop = 1.17 ATR = total risk = 0.222% of. Four-week payoff 2.07x on Est_4W (1.99x on Target_Price) - the two conventions AGREE on this name, which they do not on AIQ. SE-2 FIRES on the flat-horizon leg: Est_12W is EQUAL to Est_1W and BELOW Est_4W, and only +0.26% above the close - the estimator sees a four-week bounce and no twelve-week trend. Per SE-2 this is sized and timed as a <=4-WEEK TACTICAL SWING with a planned exit near the 4wk horizon, NOT a position hold. STATED RISK: a below-market limit into a two-sided event converts event risk into fill risk - if Nvidia disappoints after the 08-26 close, the 08-27 tape could gap XLF straight through and fill this order into weakness, with the stop only 1.30% below the limit. VOID CONDITION: if the 08-26 or 08-27 open gaps BELOW the stop, do not fill - cancel and re-evaluate. CAVEAT: PullbackBuy_VWAP is actionable at n=8 with bias +0, but its hit_4w is only 0.167 - this trade is built on the four-week leg and that family reaches its four-week target one time in six. BRANCH (ADR-0019): assumes the literal portfolio JSON (all). if the 08-25 XLY card was TAKEN, if the 08-07 XBI card was TAKEN, and ZERO SHARES if both were taken - see systemic finding 6. · news |
| AIQ | Global X AI & Tech ETF | 63.08 | DECLINED | 63.08 | 62.55 | 62.83 (-0.4%) | 63.29 (+0.3%) | 68.94 (+9.3%) | Clears the conviction floor at 74 adjusted and ranks second on the board, but the model does not expect this fund to be higher in a week: Est_1W sits BELOW the close. The four-week estimate is only +0.33% above the entry, which against a stop is a 0.40x payoff - the weakest risk-reward of any name clearing the floor. The twelve-week view is genuinely strong (+9.29%), but the trade on offer is an at-market entry, not a twelve-week position, and buying it at the 08-26 open means holding an AI-and-tech fund THROUGH the Nvidia Q2 FY2027 print after that same day's close, where the event horizon carries a two-sided -8%/+9% band on the single largest driver. A 0.50-ATR stop sits inside half a daily range; that event would take it out on almost any downside gap. Declined - the twelve-week case is real but the entry, the stop and the calendar are all wrong for it. OPERATIONAL: SE-1/L1 haircut -2 applied (FailedBreakdown_Up_20D actionable n=13, hit_1w 0.417). SE-2 fires on the 1wk leg. NOTE the method disagreement in systemic finding 1: under the Target_Price convention AIQ pays 4.00x and would rank FIRST on this board. RE-ARM: a below-close limit entry (at or under EMA20), a stop of at least 1.0 ATR, and Est_4W above the close - or simply the same print AFTER the 08-26 Nvidia event has cleared. · news |
| XBI | SPDR S&P Biotech ETF | 169.10 | HOLD | 169.78 | 160.10 | 169.17 (-0.4%) | 173.20 (+2.0%) | 178.30 (+5.0%) | The best fund on the board today, up 3.00% to and printing a fresh 52-week high, as biotech reaches its highest level since the pandemic on the Moderna/Merck mRNA cancer-therapy trial win, a friendlier FDA and heavy M&A. The book is carrying it as hold-pending on the unresolved 08-07 branch and that hold is working. But today's FRESH buy print is declined on two counts: it is 2 points below the conviction floor at 63, and it is a buy-stop at against a stop - a 3.11 ATR risk for a 0.22x four-week payoff. L1 also warns this family's four-week targets overshoot 55-75% and mean-revert, and a target is +19% in four weeks on a fund already at a 52-week high. Riding the existing exposure is right; adding to it here at a three-ATR risk is not. OPERATIONAL: STOP HELD AT, unchanged. Chandelier today = close - 2.0x ATR =, which is BELOW the recorded stop, so no raise is available and the stop is never widened. PROFIT-TAKE ARM CHECK (ADR-0012): NOT ARMED - Gain_ATR 2.60 (threshold 3.0) and T12 progress 58.8% (threshold 90%), Exit_Warning blank. No trim, no trail-raise. On the taken branch ( @ =) the position closed at = + (+8.41%), up today. The ledger-vs-memory cost-basis divergence (vs) is STILL unreconciled. ADR-0019: the 08-07 card needs 'trade buy sectoretf XBI 217 155.98' or 'trade skip sectoretf XBI'. · news |
| XLY | Consumer Discretionary SPDR | 117.95 | HOLD | 118.41 | 117.50 | 118.60 (+0.2%) | 119.91 (+1.3%) | 128.73 (+8.7%) | Yesterday's acquire executed at the 08-25 open by its own instruction - the open was, a +0.09% gap from the action price and well inside the 1.5% reprice trigger, so the order was valid - but it has NOT been recorded in the portfolio JSON, so the monitor still shows the book flat. Day one went against it: the fund fell 0.30% on a session when the S&P rose 0.32%, and the discretionary story of the day was Dick's Sporting Goods collapsing 30.68% on a guidance cut. Conviction dropped 17 points from in a single session and the low of came within - 0.17 ATR - of the recorded stop. The position is not wrong yet and the case has not broken: the twelve-week estimate is still +9.14% above the close and the four-week payoff from the actual fill is 1.65x, down from 2.63x but still above the bar. Hold. OPERATIONAL: STOP UNCHANGED at - today's model stop is and the chandelier is, both lower, and the stop is never widened. L2 does NOT fire: no close below stop and the 12wk is positive. On the assumed fill the position is worth against a cost = - (-0.39%). ADR-0019: this card is now UNDECIDED past one session - record it as 'trade buy sectoretf XLY 166 118.41' or 'trade skip sectoretf XLY'. · news |
| — | First Trust Cloud Computing ETF | — | NO ACTION | — | — | n/a | n/a | n/a | For the second consecutive session this is the best-constructed order on the board and the second consecutive session it is declined on conviction alone. It offers a genuine buy limit at, a full 1.80% below the close, a 1.16 ATR stop, a 1.78x four-week payoff, and all three horizons above both close and entry (+2.31% / +4.41% / +7.91% vs entry) - on the L1-favoured family. It fails only the hard 65 conviction floor, by 7 points, and the floor is the engine's own BUY - ADD threshold which this run does not invent a new scale to dodge. OPERATIONAL: conviction has now STALLED at exactly 58 for two sessions (trail -> rather than building, which is the change from yesterday's read. RE-ARM: conviction >= 65 with the PullbackBuy_VWAP limit still intact below the close. |
| — | iShares Biotech ETF | — | NO ACTION | — | — | n/a | n/a | n/a | Biotech is genuinely working - IBB rose 1.82% on the Moderna/Merck trial-win rally - but the anticipate slot fails on the count before economics are even reached: BUY - ANTICIPATE appeared in only ONE of the last three snapshots (WATCH 63 -> NO TRADE 0 -> ANTICIPATE 73), against the required two. Economics would have declined it regardless: a buy-stop against a stop is 3.00 ATR of risk for a 0.16x four-week payoff, RSI is 71.8 and extended, and AnticipationUp_VCP is this book's worst actionable cell at 0-for-5 on 1wk targets with the bias pinned at the -10 cap. OPERATIONAL: sixteenth consecutive session with an empty anticipate slot. The counterfactual anticipate bucket (n=23) still returns no medians at all - the family neither hits nor stops, it drifts. ADR-0019: the 07-30 and 08-06 IBB cards remain unresolved after twenty-one sessions - 'trade skip sectoretf IBB' for the 08-06 gap-guard card. |
| — | SPDR Gold Shares ETF | — | NO ACTION | — | — | n/a | n/a | n/a | The name the book has declined four times in a row prints NO TRADE at conviction 0 today, so there is no order to evaluate and the written re-arm is moot - but the running cost is recorded honestly: first declined 08-08 at, gold closed today, so the streak has now forgone +7.43%, up from +7.08%. Gold itself rose 0.69% to as the 10-year fell 6bp to 4.63%. OPERATIONAL: consensus is Conflicted (Trend 78 / Momentum 24), RSI 73.0 and extended. Had an order printed, re-arm leg 1 would have FAILED again anyway - Est_4W is -1.83% BELOW the close. RE-ARM unchanged: a non-paying-up entry (limit at or below the close, OR at/below EMA20), stop inside 2.0 ATR, and Est_4W above the close. |
| — | Health Care Select Sector SPDR | — | NO ACTION | — | — | n/a | n/a | n/a | Yesterday's queue withdrawal is vindicated at near-zero cost: XLV rose just 0.34% to, so not filling cost the book essentially nothing, and the fund has since fallen below the conviction floor to WATCH 61. The written re-arm is NOT satisfied - it requires a PullbackBuy_VWAP or MomentumContinuation_Up print with a non-paying-up entry, and XLV again prints FailedBreakdown_Up_20D at market. SE-2 fires hard: Est_12W is -3.80% BELOW the close, so the estimator sees the fund lower in three months than it is today. No action. OPERATIONAL: RSI 69.3 and extended. RE-ARM unchanged: PullbackBuy_VWAP or MomentumContinuation_Up, entry at or below the close (or at/below EMA20), stop inside 2.0 ATR, Est_4W above the close. |
| — | Consumer Staples SPDR | — | NO ACTION | — | — | n/a | n/a | n/a | Yesterday's decline is VINDICATED, and cleanly. XLP was a STRONG BUY at conviction 85 declined on a 0.92x four-week payoff; it fell 1.06% to today and the signal collapsed all the way to NO TRADE at conviction 0 on 'Consensus conflict + low conviction'. This is the first unambiguous confirmation in weeks that the payoff bar is screening out real weakness rather than merely being timid, and it is recorded here as the counterweight to the GLD streak. OPERATIONAL: consensus Conflicted (Trend 78 / Momentum 24) - the same profile GLD carries. Staples was among the worst funds on a risk-on session, exactly reversing the 08-24 defensive rotation. |
| — | SPDR Dow Jones Industrial Avg | — | NO ACTION | — | — | n/a | n/a | n/a | The Dow proxy ties out to the tape to the basis point (+0.30% against the +0.30% Dow) but sits 6 points below the conviction floor at 59 adjusted, down from 64. At-market entry, a stop, and an Est_4W of give a 1.10x four-week payoff - under the bar. No action. |
| — | SPDR S&P 500 ETF | — | NO ACTION | — | — | n/a | n/a | n/a | Ties out exactly to the +0.32% S&P 500 close of 7,677.28. WATCH at conviction 49, sixteen points below the floor, on an at-market entry with a 0.57 ATR stop. No action. |
| — | Invesco QQQ (Nasdaq-100) | — | NO ACTION | — | — | n/a | n/a | n/a | Up 0.62% against the Nasdaq Composite's +0.66% as growth caught a bid ahead of Nvidia. WATCH at 51, well below the floor, RSI 48.9 and directionless. No action - and initiating a Nasdaq-100 proxy the session before the Nvidia print would be the same mistake declined on AIQ. |
| — | iShares Russell 2000 ETF | — | NO ACTION | — | — | n/a | n/a | n/a | Up 0.42%, WATCH at 49, sixteen points below the floor. At-market entry with a 0.50 ATR stop and an Est_4W only +0.55% above the close. No action. |
| — | Roundhill Magnificent Seven ETF | — | NO ACTION | — | — | n/a | n/a | n/a | Up 0.61% on the pre-Nvidia growth bid. WATCH at 50, fifteen below the floor, and the same event objection as AIQ and QQQ applies with more force to a mega-cap-seven fund. No action. |
| — | Tech Select Sector SPDR | — | NO ACTION | — | — | n/a | n/a | n/a | Up 0.94%. WATCH at 51, below the floor, RSI 47.5. The 12wk estimate is strong at (+10.5%) but the four-week estimate is +0.18% - the same flat-horizon SE-2 profile as AIQ, and the same Nvidia event exposure. No action. |
| — | Defiance Quantum ETF | — | NO ACTION | — | — | n/a | n/a | n/a | Up 1.26% and the strongest of the sub-floor WATCH cluster at 56, up from 49. Est_4W is only +0.93% above the close against a 0.50 ATR stop. Nine points short of the floor. No action, but the conviction is building - worth watching. |
| — | iShares Semiconductor ETF | — | NO ACTION | — | — | n/a | n/a | n/a | Bounced 1.56% as Nvidia snapped a seven-day losing streak, but the signal is NO TRADE at conviction 0 on 'Consensus conflict + low conviction' with Indeterminate pillar consensus. SE-2 fires hard: Est_12W is -5.34% BELOW the close. The EMA ladder is still inverted (5 < 10 < 20 < 50). No action - a one-day bounce into an earnings print is not a signal. |
| — | VanEck Semiconductor ETF | — | NO ACTION | — | — | n/a | n/a | n/a | Up 1.65% on the same Nvidia bounce, same NO TRADE at conviction 0, same Indeterminate consensus, same inverted EMA ladder. SE-2 fires: Est_12W is -3.91% BELOW the close. No action. |
| — | Energy Select Sector SPDR | — | NO ACTION | — | — | n/a | n/a | n/a | The worst fund on the board, down 1.66% as WTI crude fell 1.68% to. NO TRADE at conviction 0, consensus Conflicted (Trend 78 / Momentum 24). No action. |
| — | Industrial Select Sector SPDR | — | NO ACTION | — | — | n/a | n/a | n/a | Down 0.34% with RSI at 38.7, the weakest momentum reading on the board. NO TRADE at conviction 0, Indeterminate consensus, price below every EMA from. No action. |
| — | Procure Space ETF (SpaceTech) | — | NO ACTION | — | — | n/a | n/a | n/a | Down 0.18% on a broadly green session and the only outright BEARISH print on the board - FailedBreakout_Down_20D, Consolidation_Bearish, price below every EMA including the 200-day. Conviction fell. This is a long-only book, so AVOID means no action, not a short. |
| — | Destiny Tech100 Inc | — | NO ACTION | — | — | n/a | n/a | n/a | The board's biggest mover, up 6.94% to on a 20-day breakout, and the only name in the book that actually prices in the fairvalue file - at OVERVALUED_VS_RI with MoS -0.78. WATCH at 48, seventeen points below the floor, and the stop is 3.11 ATR wide against a 3.5% four-week estimate. No action. |
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 →
-0.068 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.
50 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.