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 |
|---|---|---|---|---|---|---|---|---|---|
| XLE | Energy Select Sector SPDR | 62.29 | BUY — QUEUED @61.12 | 61.12 | 59.73 | 62.56 (+2.4%) | 63.15 (+3.3%) | 65.73 (+7.5%) | Energy is the one place on today's board where a genuine pullback entry exists rather than a chase. XLE fell 0.22% while the Nasdaq rose 1.57% on Nvidia's blowout, so buying it is not paying up for the AI melt-up; the fund's uptrend is intact with price above its 20-, 50- and 200-day averages, momentum improving for a second session, and — unusually for this book — the model's 12-week view sits above its 4-week view, which sits above today's close, so the forward outlook is not inverted. The order is a limit 1.9% below the close at the volume-weighted average price, with a stop 2.3% under that, giving roughly two dollars of expected gain per dollar risked. Balanced against a genuinely two-sided sector debate: energy is rated Hold after a 40% twelve-month run, and 2026 oil forecasts near Brent argue oversupply, while AI power demand and refining margins argue the other way — which is why this is sized to the cash on hand and framed as a four-week swing worked on the stop, not a long-term hold. OPS: adj cv 73 = raw 73 + val_adj 0 (NA_ETF, valuation blind) + bias +0 (PullbackBuy_VWAP n=8, the book's only non-negative actionable buy cell). L1-favoured family. Payoff clears BOTH conventions - 1.46x on Est_4W, 2.01x on Target_Price - the tiebreak that carried XLF twice; AIQ's conventions disagree 10x and XLK's 48x. SE-2 does NOT fire (Est_12W 65.73 > Est_4W 63.15 > close 62.29). Stop 1.16 ATR clears the 1.0-ATR floor. Limit is 0.97 ATR / 1.88% below close and 0.70% below today's low = fillable, unlike SKYY at 2.13 ATR. Sizing: 49.24% x x 20% = ->, CAPPED by (post-XLF-fill) -> =. Risk 259 x = = 0.72% of book. Improves on the 08-26 decline (payoff was 0.57x, now 1.46x) - a changed case, not a stale re-recommendation. 1wk estimate carries the SE-3 low-reliability flag (calib_1w -0.068). L8: action price is the 08-27 settled-close reference; reprice if the 08-28 open gaps >1.5%. VOID if the open gaps below the stop. EXPIRES 2026-09-01 - withdraw or reprice, no zombie limits. · news |
| XLF | Financial Select Sector SPDR | 57.88 | HOLD 591 @57.79 | 57.79 | 57.11 | 58.03 (+0.4%) | 58.95 (+2.0%) | 58.08 (+0.5%) | The queued financials order filled and the position is held into tomorrow's Fed event. Banks and brokers set a record close in late July on their best month since January 2025, helped by a rebound in investment-banking fees and a lighter regulatory touch, and that structural case is unchanged by today's 0.65% dip — money simply rotated into technology after Nvidia's results. The position is a fraction of a percent in profit one day in, with the protective stop 1.2% below the entry, and it is deliberately being carried through Friday's Jackson Hole keynote rather than trimmed ahead of it: the event is genuinely two-sided, with markets pricing roughly 40% odds of a September rate rise, and pre-emptively cutting a position because a speech is scheduled is not a reason, it is a flinch. The stop is the discipline. OPS: FILL CONFIRMED ON THE TAPE - 08-27 low took out the GTC limit; open never triggered the void condition. @ =; marked =, + (+0.16%). NOTE: the 08-25 limit of would have MISSED BY ONE CENT - the 08-26 provenance reprice is the entire difference between this fill and a 27th withdrawal. direction:none deliberately - the 08-26 buy card carries the grade, this line records the fill without double-counting. ADR-0012 arm check: NOT ARMED (Gain_ATR 0.16 vs 3.0, T12 progress nil, Exit_Warning blank) - no trim. Trail-raise NOT available: chandelier - 2.0 x =, BELOW the recorded stop. STOP UNCHANGED; risk 591 x = = 0.80% of book. Conviction eased = 12 pts, short of the 20-pt collapse tick. SE-2 FIRES (Est_12W < Est_4W) - <=4-week tactical swing, not a position hold. ADR-0019 URGENT: 'trade buy sectoretf XLF 591 57.79' - the monitor reports trades_detected:[] and cannot surveil the stop on a position it does not know exists. · news |
| SKYY | First Trust Cloud Computing ETF | 166.60 | DECLINED | 157.80 | 153.02 | 165.77 (+5.1%) | 170.09 (+7.8%) | 176.81 (+12.0%) | Cloud software was the day's biggest winner — the fund rose 4.2% as Okta jumped 28% and Salesforce had its best day in six years — and that is precisely the problem. The only entry the model will sanction sits more than 5% below today's close and over 3% below the day's low, so taking the trade would mean waiting for the entire rally to be given back. A good setup at a price that will not be reached is not a trade. Re-arm if it pulls back toward OPS: highest adj cv on the board (85, bias +0). Payoff excellent - 2.57x Est_4W, 2.00x Target - and stop is 1.16 ATR. DECLINED PURELY ON FILLABILITY: limit is 2.13 ATR / 5.28% below the close and 3.31% below today's low, on a +4.21% session. 26 consecutive unfilled queue entries say a 2.13-ATR discount is a decline dressed as an order (cf. XLF's 0.03-ATR limit, which filled today). RE-ARM: pullback toward with the printed Entry_Price within ~1.0 ATR of the close. |
| AIQ | Global X AI & Tech ETF | 64.54 | DECLINED | 64.54 | 63.77 | 65.12 (+0.9%) | 64.75 (+0.3%) | 69.31 (+7.4%) | Rank one on the board, and declined anyway. The fund rose 2.3% on Nvidia's results and closed one cent off its high of the day, so buying at the model's price means paying the very top tick of an earnings reaction — the exact pattern that tends to round-trip within days. The four-week outlook is only a third of a percent above that price, against a stop so tight it would flatter any trade, so there is almost no reward for the risk even if the entry were fair. OPS: adj 83 (raw 85, bias -2 FailedBreakdown). L6 fires squarely - post-earnings gap-chase, at-market at = close = 1c off the high on a +2.33% NVDA-reaction session. Payoff 0.27x on Est_4W (+0.33% over entry) against a 0.72-ATR stop = sub-ATR artefact. The two payoff conventions disagree 10x (0.27x Est_4W vs 2.77x Target_Price) - systemic finding 2. Declined on geometry AND payoff. |
| SPY | SPDR S&P 500 ETF | 771.10 | DECLINED | 771.10 | 767.16 | 771.34 (+0.0%) | 777.24 (+0.8%) | 784.54 (+1.7%) | The closest call of the day, and worth being honest about: on reward-versus-risk alone the broad index would have been the second purchase. It is declined on everything around the number — the entry the model prints is exactly today's closing price, so there is nothing to queue below and no discount to wait for; the protective stop is unusually tight; the signal family is the weakest one this book tracks; and it amounts to buying the whole market at the close of a Nvidia-driven session with a Fed keynote twelve hours away and limited cash left. OPS: adj 73 (raw 75, bias -2). Payoff genuinely CLEARS - 1.56x Est_4W, 2.53x Target - and the forward is non-inverted (Est_12W 784.54 > Est_4W 777.24 > close 771.10). Declined on the S6 tuple, not the number: FailedBreakdown at bias -2 (hit_4w 0.30, stop_first ~0.6); 0.79-ATR sub-ATR stop; Entry_Price == Close exactly so nothing is queueable; Jackson Hole Warsh keynote 08-28 10:00 ET; only and XLE has the better tuple. If the payoff bar were the sole test this is the second acquire - see systemic finding 2 on why that bar must be written down. |
| XLK | Tech Select Sector SPDR | 188.61 | DECLINED | 188.61 | 185.67 | 189.41 (+0.4%) | 188.77 (+0.1%) | 203.08 (+7.7%) | Technology was the best of the eleven S&P sectors today and this fund rose 3.2%, closing twelve cents off its high — and the model's own four-week view sits less than a tenth of a percent above that closing price. Paying the top of a 3% move for an outlook that has already caught up to it is not a trade, it is momentum with no margin. OPS: adj 73 (raw 75, bias -2). Payoff 0.05x on Est_4W (+0.08% over entry) - the purest instance on the board of the SE-2 lag artefact, which fires hardest on broad up sessions (systemic finding 4). Target_Price convention would read 2.60x - a 48x disagreement. At-market at close on a +3.16% NVDA-reaction day; L6 fires. 0.77-ATR stop. |
| MAGS | Roundhill Magnificent Seven ETF | 68.60 | DECLINED | 68.60 | 67.59 | 68.99 (+0.6%) | 69.26 (+1.0%) | 73.79 (+7.6%) | The mega-cap basket rose 1.5% on Nvidia's beat and closed nine cents off its high, with the model's four-week view less than a percent above that price — under two-thirds of a dollar of expected gain for every dollar risked. The direction is right and the price is wrong. OPS: adj 73 (raw 75, bias -2 FailedBreakdown). Payoff 0.65x on Est_4W; Target_Price convention 1.70x. At-market with Entry_Price == Close on a +1.52% session; L6 applies. Stop 1.18 ATR is well constructed - the geometry is not the problem, the payoff is. |
| DIA | SPDR Dow Jones Industrial Avg | 535.22 | DECLINED | 535.22 | 532.94 | 535.90 (+0.1%) | 536.56 (+0.3%) | 541.35 (+1.1%) | The Dow barely participated, up 0.19% while the Nasdaq rose 1.6%, and the model's four-week view is a quarter of a percent above the entry — roughly sixty cents of expected gain against of risk. There is no case here beyond the label. OPS: adj 68 (raw 70, bias -2). Payoff 0.59x Est_4W (3.27x on Target_Price - another wide convention gap). 0.61-ATR stop = sub-ATR artefact. At-market at close. NOTE: DIA +0.19% ties out EXACTLY to the reported Dow +0.19% - the scan's daily accuracy check passes again. |
| DXYZ | Destiny Tech100 Inc | 35.40 | DECLINED | 30.85 | 28.32 | 35.36 (+14.6%) | 36.43 (+18.1%) | 37.00 (+19.9%) | The only holding in this book that can actually be valued, and it screens expensive against its own book value. Beyond that the entry is not reachable: the model wants to buy nearly 13% below today's close and more than 9% below the day's low, on a fund that just rose 2.5%. OPS: adj 67 = raw 71 + val_adj -4 (OVERVALUED_VS_RI, MoS -0.78, the book's ONLY non-NA fairvalue row; quality gate F but it blocks new entries only and the geometry kills this first). Limit vs close = 12.85% / 2.09 ATR below, and 9.29% below today's low. Unfillable by an order of magnitude. high_vol tier. |
| GLD | SPDR Gold Shares ETF | 422.60 | DECLINED | 422.60 | 418.43 | 424.57 (+0.5%) | 410.29 (-2.9%) | 435.30 (+3.0%) | Gold has now run 6% since this book first passed on it three weeks ago — the single most expensive thing it has declined — and it still would not qualify today. The model's own four-week estimate sits nearly 3% BELOW the current price, so on its own numbers the fund is expected to be cheaper in a month than it is now. Recording the miss, not chasing it. OPS: below the 65 floor at WATCH 62. Decline streak opened 08-08 at; now = +6.06% forgone (was +5.73% on 08-26), still the largest single cost in this book's decline ledger and recorded every session. Fails payoff leg 1 outright: Est_4W is -2.91% below the close - negative numerator. SE-2 fires. |
| — | Invesco QQQ (Nasdaq-100) | — | NO ACTION | — | — | n/a | n/a | n/a | Below the action threshold once the weak signal family is discounted, and in any case it is the index that just rose 1.4% on Nvidia's results — the wrong moment to buy it at the close. OPS: raw 65 -> adj 63, under the 65 floor on the -2 FailedBreakdown haircut alone. Payoff 1.15x Est_4W. At-market at close on a +1.37% session; L6 applies. |
| — | VanEck Semiconductor ETF | — | NO ACTION | — | — | n/a | n/a | n/a | Bearish label, long-only book, so no action either way. Flagging it as a data-quality concern rather than a trade: the model called this fund a failed breakdown on the very day it rose 3.1% following Nvidia's beat. OPS: AVOID cv76 on FailedBreakout_Down_20D on a +3.10% session, hours after NVDA beat and raised. Flipped from NO TRADE cv0 x3. Est_12W sits BELOW the close (SE-2). Systemic finding 5: the FailedBreakout_Down_20D trigger should be sanity-checked against same-session return - prima facie mislabelled. |
| — | iShares Semiconductor ETF | — | NO ACTION | — | — | n/a | n/a | n/a | No signal. The model has had nothing to say about semiconductors through the entire Nvidia run-up and through the reaction itself. OPS: NO TRADE cv0, 'Consensus conflict + low conviction', on a +1.95% session - fourth consecutive cv0 print spanning the whole NVDA cycle. Est_12W vs close (SE-2). Paired with SMH in systemic finding 5. |
| — | Procure Space ETF (SpaceTech) | — | NO ACTION | — | — | n/a | n/a | n/a | Bearish and long-only, so nothing to do. Space remains the one corner of the board with no participation at all — it sits below its 20-, 50- and 200-day averages with weak momentum. OPS: AVOID cv67, Consolidation_Bearish consensus, RSI 40.9, 3.55% below VWAP, price under EMA20/50/200. Fourth consecutive AVOID. |
| — | SPDR S&P Biotech ETF | — | NO ACTION | — | — | n/a | n/a | n/a | No signal for a second straight session, and the fund drifted lower while the market rallied. OPS: NO TRADE cv0, 'Consensus conflict + low conviction', -0.10% on a +0.72% S&P day. Second consecutive cv0 - NOT the sustained-NoTrade exit basis on the literal-JSON branch, where the book is flat. ADR-0019: the 08-07 branch ( @) is now THIRTEEN sessions unresolved and on that branch is a winner, which per 08-26's finding never self-heals - it distorts sizing every single run. Priority 2 behind the XLF fill. |
| — | iShares Biotech ETF | — | NO ACTION | — | — | n/a | n/a | n/a | No signal, second consecutive session. Momentum has rolled over even though the longer trend is still up. OPS: NO TRADE cv0, Conflicted consensus (Trend bullish, Momentum bearish), RSI 68.9. The 08-25 BUY-ANTICIPATE at cv73 lasted exactly one day - which is what the 2-of-3 anticipate count exists to catch. ADR-0019: the 08-06 gap-guard card is TWENTY-FOUR sessions open; 'trade skip sectoretf IBB' costs the book nothing. |
| — | Health Care Select Sector SPDR | — | NO ACTION | — | — | n/a | n/a | n/a | No signal, and the fund fell 1.1% on a rising market. The model's twelve-week view is now below today's price. OPS: NO TRADE cv0, Conflicted (Momentum bearish vs Trend bullish). Second consecutive cv0. The full ladder since 08-24 reads STRONG BUY 85 -> BUY 72 -> WATCH 61 -> NO TRADE 0 -> NO TRADE 0 - the 08-24 withdrawal at a limit is vindicated outright. Est_12W is -3.85% below the close (SE-2). |
| — | Industrial Select Sector SPDR | — | NO ACTION | — | — | n/a | n/a | n/a | No signal. Yesterday's board leader is today's laggard, down 0.9% with price now below its 20- and 50-day averages. OPS: NO TRADE cv0, Indeterminate consensus, RSI 41.5, close below EMA20 and EMA50, 2.32% below VWAP. Fourth consecutive cv0. Led the board at +1.09% on 08-26 - a clean example of this book's ~1-2 session signal half-life (pending draft S2). |
| — | Consumer Staples SPDR | — | NO ACTION | — | — | n/a | n/a | n/a | Below the action threshold, and staples were the worst sector on the board as money moved the other way. The model's four-week view is below the current price. OPS: WATCH 56 -> adj 54, under the 65 floor. -1.38%, worst print on the board. Est_4W is -0.73% below the close - negative payoff numerator (SE-2). The 08-24 decline at STRONG BUY 85 is now -2.71% cumulative across three sessions - vindicated. |
| — | Consumer Discretionary SPDR | — | NO ACTION | — | — | n/a | n/a | n/a | Below the action threshold and still falling — down another 1.1% on a rising market, the day after the stop closed out the position. The exit is looking correct. OPS: WATCH 52 -> adj 50. Conviction ladder -> -> 52. Stopped out 08-26 at for -0.77%; the fund has fallen a further -1.09% since, so the stop saved roughly on the 166-share branch. RE-ARM still gated: no re-entry below cv65. ADR-0019: the compounded card needs 'trade buy 166 118.41' + 'trade sell 166 117.50', or a single skip. |
| — | iShares Russell 2000 ETF | — | NO ACTION | — | — | n/a | n/a | n/a | Below the action threshold. Small caps managed only +0.3% while the Nasdaq rose 1.6% — no broadening in this rally. OPS: WATCH 59 -> adj 57, under the floor. Conviction improved but the label has been WATCH for four straight sessions. Entry_Price == Close, nothing queueable. 0.66-ATR stop. |
| — | Defiance Quantum ETF | — | NO ACTION | — | — | n/a | n/a | n/a | One point short of the action threshold before the signal-family discount, and two after. Rose 1.5% with the tech complex but the entry is the closing price, so there is nothing to wait for. OPS: WATCH 64 -> adj 62. Closest of the four sub-floor WATCH names. Payoff 0.82x Est_4W. Entry_Price == Close on a +1.47% session. high_vol tier. Worth watching if it prints a genuine below-close pullback limit. |
Outcome & track record
Accuracy at the time of this record.
34 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.